@sogni-ai/sogni-protocol 1.0.0-alpha.47 → 1.0.0-alpha.49

package/catalogs/seedance-reference-limits.json

@@ -24,6 +24,12 @@
       "videos": 10,
       "audios": 10,
       "assets": 50
+    },
+    "seedance-2-5-uncensored": {
+      "images": 30,
+      "videos": 10,
+      "audios": 10,
+      "assets": 50
     }
   }
 }

package/manifests/generation-tools.json

@@ -71,7 +71,7 @@
                 "pony-faetality",
                 "dreamshaper-xl"
               ],
-              "description": "DO NOT SET THIS PARAMETER unless the user names a specific model, asks for a very complex image render, asks for a video storyboard/storyboard sheet/contact sheet/panel layout image, asks for anime without naming a model, requests permitted NSFW/nudity content, or explicitly asks for Z-image/Z-image Turbo/Krea 2 Turbo image-to-image. The app auto-selects based on quality settings. Set \"gpt-image-2\" when the user explicitly asks for legacy GPT Image 2. Set \"gpt-image-2.5-sunburst\" by default for complex single-image renders that need very strong text rendering, dense labels, crisp typography, multi-panel composition, timing notes, foley notes, professional storyboard-sheet layout, or a comprehensive character/mascot/model sheet with turnarounds, expressions, accessories, palette swatches, and brand notes. Set \"one-obsession-v22\" when the user asks for an anime or anime-style image and has not named a specific image model. Set \"z-turbo\" when the user asks for Z-image Turbo; set \"z-image\" when they ask for Z-image without Turbo. Set \"krea-2-turbo\" when the user asks for Krea 2 Turbo. If the user names another image model, honor that requested model instead. A model preference usually does not change which tool to use; the Z-image and Krea 2 Turbo image-to-image exception uses sourceImageIndex plus starting_image_strength on this tool. NSFW rule: \"gpt-image-2\"/Qwen image models CANNOT do nudity. For permitted NSFW/nudity content, prefer \"dark-beast-krea2\", then \"dark-beast-z-turbo\"; \"chroma1-hd\", \"pony-v7\", \"chroma-detail\", \"chroma-v46-flash\", and \"z-turbo\" are compatible fallbacks. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
+              "description": "DO NOT SET THIS PARAMETER unless the user names a specific model, asks for a very complex image render, asks for a video storyboard/storyboard sheet/contact sheet/panel layout image, asks for anime without naming a model, requests permitted NSFW/nudity content, or explicitly asks for Z-image/Z-image Turbo/Krea 2 Turbo image-to-image. The app auto-selects based on quality settings. Set \"gpt-image-2.5-flare\" when the user asks for a ChatGPT, OpenAI, GPT, or GPT Image image/model without naming a version. Set \"gpt-image-2\" only when the user explicitly names GPT Image 2, GPT-2, or gpt-image-2; GPT Image 2 is never a default. Set \"gpt-image-2.5-sunburst\" when the user explicitly requests very strong text rendering, and by default for video storyboards and other complex single-image renders that need dense labels, crisp typography, multi-panel composition, timing notes, foley notes, professional storyboard-sheet layout, or a comprehensive character/mascot/model sheet with turnarounds, expressions, accessories, palette swatches, and brand notes. Set \"one-obsession-v22\" when the user asks for an anime or anime-style image and has not named a specific image model. Set \"z-turbo\" when the user asks for Z-image Turbo; set \"z-image\" when they ask for Z-image without Turbo. Set \"krea-2-turbo\" when the user asks for Krea 2 Turbo. If the user names another image model, honor that requested model instead. A model preference usually does not change which tool to use; the Z-image and Krea 2 Turbo image-to-image exception uses sourceImageIndex plus starting_image_strength on this tool. NSFW rule: GPT Image models and Qwen image models CANNOT do nudity. For permitted NSFW/nudity content, prefer \"dark-beast-krea2\", then \"dark-beast-z-turbo\"; \"chroma1-hd\", \"pony-v7\", \"chroma-detail\", \"chroma-v46-flash\", and \"z-turbo\" are compatible fallbacks. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
             },
             "width": {
               "type": "number",
@@ -177,7 +177,7 @@
       "type": "function",
       "function": {
         "name": "generate_video",
-        "description": "Generate a video from text or Seedance multimodal references. LTX 2.5 is the default and generates audio natively; LTX 2.3 remains available as rollback and also generates audio natively (dialogue, sounds, ambient music) — describe audio in the prompt. If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Never use placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. For non-Seedance syncing to a specific song or audio track, use sound_to_video instead. For non-Seedance animation from a locked source photo, use animate_photo. Do NOT use for My Personas unless generating a Seedance reference-based video — standard persona videos use resolve_personas → edit_image → animate_photo. SEEDANCE DEFAULT: For seedance2, seedance2-mini, or seedance2-5, default to exactly one video (4-15s on 2.0/Mini, 4-30s on seedance2-5) unless the user explicitly asks for multiple separate outputs. Multiple beats, shots, or scene descriptions in one up-to-15s Seedance prompt are still one video. If the user requests one continuous Seedance video longer than 15s, prefer seedance2-5, which renders up to 30s in a single call; beyond 30s (or on 2.0/Mini) preserve the requested total duration in the prompt/context and let chat orchestration split it into supported segment renders and stitch them instead of clamping it to a short excerpt. Uploaded/generated storyboard, shot-sheet, or trailer-concept images used as Seedance references should become one Seedance 2.5 generate_video call at targetResolution=1080 by default; preserve an explicitly requested model or resolution, and use Seedance 2.0 for 4K because Seedance 2.5 supports up to 1080p. Do not extract panels with edit_image and do not animate the storyboard sheet with LTX unless the user explicitly asks for separate non-Seedance clips. Seedance loose image, video, and audio references go through this tool; do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. If the uploaded audio is the primary sync target, lip-sync target, or requested as sound-to-video/audio-sync, use sound_to_video with videoModel=\"seedance2-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render and audit the composite board, generate one scene reference still per approved scene with GPT Image 2.5 Sunburst, render each scene as a Seedance 2.5 video segment at targetResolution=1080, then stitch the segments. Preserve an explicit alternate model or resolution. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent. WAN 3 uses the exact selector wan3.0-video: use this tool for text-to-video or loose Image 1/Video 1/Audio 1 references; use animate_photo for native first/last frames and sound_to_video when audio drives timing. A Wan 3 video reference conditions a new generation; it does not invoke a provider-backed edit or extend mode. Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; use this tool for prompt-only or loose-reference generation, and never combine loose references with frame anchors.",
+        "description": "Generate a video from text or Seedance multimodal references. LTX 2.5 is the default and generates audio natively; LTX 2.3 remains available as rollback and also generates audio natively (dialogue, sounds, ambient music) — describe audio in the prompt. If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Never use placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. For non-Seedance syncing to a specific song or audio track, use sound_to_video instead. For non-Seedance animation from a locked source photo, use animate_photo. Do NOT use for My Personas unless generating a Seedance reference-based video — standard persona videos use resolve_personas → edit_image → animate_photo. SEEDANCE DEFAULT: For seedance2, seedance2-mini, seedance2-5, or seedance2-5-uncensored, default to exactly one video (4-15s on 2.0/Mini, 4-30s on seedance2-5 and seedance2-5-uncensored) unless the user explicitly asks for multiple separate outputs. Multiple beats, shots, or scene descriptions in one up-to-15s Seedance prompt are still one video. If the user requests one continuous Seedance video longer than 15s, prefer seedance2-5, which renders up to 30s in a single call; beyond 30s (or on 2.0/Mini) preserve the requested total duration in the prompt/context and let chat orchestration split it into supported segment renders and stitch them instead of clamping it to a short excerpt. Uploaded/generated storyboard, shot-sheet, or trailer-concept images used as Seedance references should become one Seedance 2.5 generate_video call at targetResolution=1080 by default; preserve an explicitly requested model or resolution, and use Seedance 2.0 for 4K because Seedance 2.5 supports up to 1080p. Do not extract panels with edit_image and do not animate the storyboard sheet with LTX unless the user explicitly asks for separate non-Seedance clips. Seedance loose image, video, and audio references go through this tool; do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. If the uploaded audio is the primary sync target, lip-sync target, or requested as sound-to-video/audio-sync, use sound_to_video with videoModel=\"seedance2-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render and audit the composite board, generate one scene reference still per approved scene with GPT Image 2.5 Sunburst, render each scene as a Seedance 2.5 video segment at targetResolution=1080, then stitch the segments. Preserve an explicit alternate model or resolution. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent. WAN 3 uses the exact selector wan3.0-video: use this tool for text-to-video or loose Image 1/Video 1/Audio 1 references; use animate_photo for native first/last frames and sound_to_video when audio drives timing. A Wan 3 video reference conditions a new generation; it does not invoke a provider-backed edit or extend mode. Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; use this tool for prompt-only or loose-reference generation, and never combine loose references with frame anchors.",
         "parameters": {
           "type": "object",
           "properties": {
@@ -236,6 +236,7 @@
                 "seedance2",
                 "seedance2-mini",
                 "seedance2-5",
+                "seedance2-5-uncensored",
                 "minimax-h3-t2v",
                 "minimax-h3-t2v-turbo",
                 "minimax-h3-fasth3-t2v-turbo",
@@ -250,7 +251,7 @@
                 "wan3.0-video",
                 "wan3.0-spicy-video"
               ],
-              "description": "\"ltx25\" (default): LTX 2.5 with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Video model. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio. \"minimax-h3-t2v\": standard 20-step MiniMax H3 text-to-video; \"minimax-h3-t2v-turbo\": the existing 4-step LightX2V Turbo text-to-video; \"minimax-h3-fasth3-t2v-turbo\": the separate FastVideo VSA four-step FastH3 engine, about 2x faster and fixed to Euler/simple; \"minimax-h3-fasth3-t2v-turbo-2stage\": the two-stage FastH3 engine: FastH3 renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length and audio. targetResolution picks the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second, and 720 renders a 384px canvas (672x384 is delivered at 1344x768) for the regular FastH3 price of 4 Spark per second. The estimate prices every request. It takes the same inputs, durations and LoRAs as \"minimax-h3-fasth3-t2v-turbo\". Choose it when the user asks for 1080p, 1440p or 2K MiniMax H3 output, for two-stage output, or for the sharpest/best H3 quality; for ordinary 768p FastH3 output keep the regular FastH3 selector at targetResolution 768. All use native audio, fixed 24fps, 5.17-15.08s, and a 768p-class 32px-grid canvas; use animate_photo for H3 image-conditioned modes. Base and Turbo T2V/I2V/FLF2V prompts use the exact ordered fields integrated_multimodal_description, overall_soundscape, and non_diegetic_music; I2V/FLF2V prepend the official alignment line. \"minimax-h3-r2v\": standard 20-step MiniMax H3 reference-to-video; \"minimax-h3-r2v-turbo\": the dedicated LightX2V 4-step Ref2VA Turbo workflow using Euler/simple and a 960x544 default. \"minimax-h3-r2v-2stage\" (Standard, 20 steps, res_multistep/simple) and \"minimax-h3-r2v-balanced-2stage\" (Balanced, 8 steps, Euler/simple) are the two-stage reference-to-video forms: the tier renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length, audio and references. targetResolution names the delivered class exactly as for the FastH3 two-stage selectors: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088), 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536), and 720 renders a 384px canvas (672x384 is delivered at 1344x768). Each bills its tier's own per-second rate plus the two-stage surcharge of the delivered class (none at 720p); the estimate prices every request. Choose one when the user asks for 1080p, 1440p or 2K MiniMax H3 reference-to-video output; keep the one-stage \"minimax-h3-r2v\" or Balanced selector for ordinary 768p output. FastH3 has no R2V mode. Every R2V selector accepts up to 9 images, 3 videos, and 3 audios (12 files total); at least one visual reference (image or video) is required and audio alone is invalid. Select references with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and address them with the official <Subject N>/<Picture N>/<Video N>/<Audio N> semantics. Seedance quality is selected only by model: use \"seedance2-mini\" for Seedance 2.0 Mini or faster/lower-cost 720p iteration, use \"seedance2-5\" at targetResolution=1080 for generated/uploaded storyboard images and current high-quality Seedance generation unless the user explicitly requests another model or resolution, and use \"seedance2\" for Seedance 2.0 or 4K requests because Seedance 2.5 supports up to 1080p. Do not use Default Media Quality Fast/HQ/Pro to represent Seedance quality. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. Seedance supports multimodal loose reference assets. Seedance 2.0 and Mini accept up to 9 images, 3 videos, and 3 audios, with no more than 12 asset files total. Seedance 2.5 accepts up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Use @Image1/@Video1/@Audio1 style references in creative briefs when assigning roles. Assign every useful reference asset a role and prefer positive preservation constraints. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. Alibaba HappyHorse 1.1 video models (third-party vendor — requires Premium Spark). Select by mode: \"happyhorse-1.1-t2v\" for text-to-video, \"happyhorse-1.1-i2v\" for image-to-video from one first-frame image, and \"happyhorse-1.1-r2v\" for reference-to-video with up to 9 reference images. Resolutions 720P and 1080P; duration 3-15 seconds at 24 fps; native synchronized audio is always generated (do not set generateAudio or negativePrompt). Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9. HappyHorse 1.1 takes image references only and renders a native synchronized audio track (always on; do not set generateAudio or a negative prompt). Pick the model by mode: happyhorse-1.1-t2v for text-to-video (no reference image), happyhorse-1.1-i2v for image-to-video from a single first frame, and happyhorse-1.1-r2v for reference-to-video with 1 to 9 reference images. For r2v, tag the images in the prompt as [Image 1]…[Image 9] and assign each a clear role. HappyHorse does not accept reference videos or reference audios. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension."
+              "description": "\"ltx25\" (default): LTX 2.5 with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Video model. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio. \"minimax-h3-t2v\": standard 20-step MiniMax H3 text-to-video; \"minimax-h3-t2v-turbo\": the existing 4-step LightX2V Turbo text-to-video; \"minimax-h3-fasth3-t2v-turbo\": the separate FastVideo VSA four-step FastH3 engine, about 2x faster and fixed to Euler/simple; \"minimax-h3-fasth3-t2v-turbo-2stage\": the two-stage FastH3 engine: FastH3 renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length and audio. targetResolution picks the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second, and 720 renders a 384px canvas (672x384 is delivered at 1344x768) for the regular FastH3 price of 4 Spark per second. The estimate prices every request. It takes the same inputs, durations and LoRAs as \"minimax-h3-fasth3-t2v-turbo\". Choose it when the user asks for 1080p, 1440p or 2K MiniMax H3 output, for two-stage output, or for the sharpest/best H3 quality; for ordinary 768p FastH3 output keep the regular FastH3 selector at targetResolution 768. All use native audio, fixed 24fps, 5.17-15.08s, and a 768p-class 32px-grid canvas; use animate_photo for H3 image-conditioned modes. Base and Turbo T2V/I2V/FLF2V prompts use the exact ordered fields integrated_multimodal_description, overall_soundscape, and non_diegetic_music; I2V/FLF2V prepend the official alignment line. \"minimax-h3-r2v\": standard 20-step MiniMax H3 reference-to-video; \"minimax-h3-r2v-turbo\": the dedicated LightX2V 4-step Ref2VA Turbo workflow using Euler/simple and a 960x544 default. \"minimax-h3-r2v-2stage\" (Standard, 20 steps, res_multistep/simple) and \"minimax-h3-r2v-balanced-2stage\" (Balanced, 8 steps, Euler/simple) are the two-stage reference-to-video forms: the tier renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length, audio and references. targetResolution names the delivered class exactly as for the FastH3 two-stage selectors: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088), 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536), and 720 renders a 384px canvas (672x384 is delivered at 1344x768). Each bills its tier's own per-second rate plus the two-stage surcharge of the delivered class (none at 720p); the estimate prices every request. Choose one when the user asks for 1080p, 1440p or 2K MiniMax H3 reference-to-video output; keep the one-stage \"minimax-h3-r2v\" or Balanced selector for ordinary 768p output. FastH3 has no R2V mode. Every R2V selector accepts up to 9 images, 3 videos, and 3 audios (12 files total); at least one visual reference (image or video) is required and audio alone is invalid. Select references with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and address them with the official <Subject N>/<Picture N>/<Video N>/<Audio N> semantics. Seedance quality is selected only by model: use \"seedance2-mini\" for Seedance 2.0 Mini or faster/lower-cost 720p iteration, use \"seedance2-5\" at targetResolution=1080 for generated/uploaded storyboard images and current high-quality Seedance generation unless the user explicitly requests another model or resolution, and use \"seedance2\" for Seedance 2.0 or 4K requests because Seedance 2.5 supports up to 1080p. Do not use Default Media Quality Fast/HQ/Pro to represent Seedance quality. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. \"seedance2-5-uncensored\": Seedance 2.5 Uncensored — the uncensored variant of Seedance 2.5, with every mode, resolution, duration, reference limit, and output option described for \"seedance2-5\". Choose it only when the user asks for Seedance 2.5 Uncensored (including \"Seedance Uncensored\" or \"Seedance Spicy\") or for uncensored Seedance output; never swap it in for \"seedance2-5\" otherwise. Each account must accept a one-time likeness and consent agreement in the Sogni app before its first render; until then the job fails with error 4103, so tell the user to accept it in the Sogni app instead of retrying. Seedance supports multimodal loose reference assets. Seedance 2.0 and Mini accept up to 9 images, 3 videos, and 3 audios, with no more than 12 asset files total. Seedance 2.5 accepts up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Use @Image1/@Video1/@Audio1 style references in creative briefs when assigning roles. Assign every useful reference asset a role and prefer positive preservation constraints. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. Alibaba HappyHorse 1.1 video models (third-party vendor — requires Premium Spark). Select by mode: \"happyhorse-1.1-t2v\" for text-to-video, \"happyhorse-1.1-i2v\" for image-to-video from one first-frame image, and \"happyhorse-1.1-r2v\" for reference-to-video with up to 9 reference images. Resolutions 720P and 1080P; duration 3-15 seconds at 24 fps; native synchronized audio is always generated (do not set generateAudio or negativePrompt). Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9. HappyHorse 1.1 takes image references only and renders a native synchronized audio track (always on; do not set generateAudio or a negative prompt). Pick the model by mode: happyhorse-1.1-t2v for text-to-video (no reference image), happyhorse-1.1-i2v for image-to-video from a single first frame, and happyhorse-1.1-r2v for reference-to-video with 1 to 9 reference images. For r2v, tag the images in the prompt as [Image 1]…[Image 9] and assign each a clear role. HappyHorse does not accept reference videos or reference audios. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension."
             },
             "generateAudio": {
               "type": "boolean",
@@ -287,7 +288,7 @@
             },
             "targetResolution": {
               "type": "number",
-              "description": "Short-side video resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact pixels or an output orientation. This is resolution only, not a Seedance quality tier: Seedance quality is selected by videoModel (\"seedance2\" vs \"seedance2-mini\" vs \"seedance2-5\"). Seedance 2.0 full supports 4K; Seedance Mini supports 480p/720p; Seedance 2.5 supports 480p/720p/1080p, so never set 4K for \"seedance2-5\". Wan 3 supports exactly 480p, 720p, and 1080p. HappyHorse supports only 720p and 1080p. Never set 4K for Wan 3 or HappyHorse. MiniMax H3 renders inside a 1344x768 pixel budget on a 32px grid, so use 768 for the regular H3 selectors and never 1080p or 4K. The two-stage H3 selector \"minimax-h3-fasth3-t2v-turbo-2stage\" delivers twice the canvas, so there targetResolution names the delivered short-edge class: 1080 (544px canvas short edge: 960x544 delivered at 1920x1088), 1440 for 2K (the 1344x768 canvas delivered at 2688x1536), or 720 (384px canvas: 672x384 delivered at 1344x768); omit it for 2K. Never set 4K for H3. Do not set targetResolution from Default Media Quality Fast/HQ/Pro. If omitted for Seedance, Wan 3, HappyHorse, or MiniMax H3, the host uses the selected model default. This preserves/inherits the current video shape instead of forcing landscape. Do NOT set width, height, or exact-pixel aspectRatio for bare named resolution requests. If the user says \"720p portrait\", \"720p landscape\", \"4K portrait\", or \"4K landscape\", use exact width/height/aspectRatio instead."
+              "description": "Short-side video resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact pixels or an output orientation. This is resolution only, not a Seedance quality tier: Seedance quality is selected by videoModel (\"seedance2\" vs \"seedance2-mini\" vs \"seedance2-5\"). Seedance 2.0 full supports 4K; Seedance Mini supports 480p/720p; Seedance 2.5 supports 480p/720p/1080p, so never set 4K for \"seedance2-5\" or \"seedance2-5-uncensored\". Wan 3 supports exactly 480p, 720p, and 1080p. HappyHorse supports only 720p and 1080p. Never set 4K for Wan 3 or HappyHorse. MiniMax H3 renders inside a 1344x768 pixel budget on a 32px grid, so use 768 for the regular H3 selectors and never 1080p or 4K. The two-stage H3 selector \"minimax-h3-fasth3-t2v-turbo-2stage\" delivers twice the canvas, so there targetResolution names the delivered short-edge class: 1080 (544px canvas short edge: 960x544 delivered at 1920x1088), 1440 for 2K (the 1344x768 canvas delivered at 2688x1536), or 720 (384px canvas: 672x384 delivered at 1344x768); omit it for 2K. Never set 4K for H3. Do not set targetResolution from Default Media Quality Fast/HQ/Pro. If omitted for Seedance, Wan 3, HappyHorse, or MiniMax H3, the host uses the selected model default. This preserves/inherits the current video shape instead of forcing landscape. Do NOT set width, height, or exact-pixel aspectRatio for bare named resolution requests. If the user says \"720p portrait\", \"720p landscape\", \"4K portrait\", or \"4K landscape\", use exact width/height/aspectRatio instead."
             },
             "numberOfVariations": {
               "type": "number",
@@ -534,7 +535,7 @@
                 "krea-identity-edit",
                 "dark-beast-krea2-identity-edit"
               ],
-              "description": "The app auto-selects Fast→Qwen Lightning and HQ/Pro→full Qwen only for ordinary identity-neutral edits. REQUIRED IDENTITY DEFAULT: set \"krea-identity-edit\" whenever an edit of a referenced person or character must keep likeness or character identity while changing clothing, hair or makeup, pose or position, face/head/body, background, lighting, or visual style. Infer that semantic intent in any language; never route from keyword or regex matching. Also use it for a non-Pro single-character sheet. This default applies even when the user did not name Krea; an explicitly requested model always wins. Set \"dark-beast-krea2-identity-edit\" only when the user explicitly requests that model, its uncensored/community variant, or dark_beast_krea2_identity_edit_v1_2. Set \"gpt-image-2\" when the user explicitly names legacy GPT Image 2. Set \"gpt-image-2.5-sunburst\" when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets may use Sunburst. If GPT Image 2.5 Sunburst is unavailable for detail-critical layout work, fall back to full \"qwen\", never \"qwen-lightning\". Krea identity edit models require at least one reference image, accept up to two context images, and work best at 512-2048px. Let the model tier and worker choose current steps, guidance, sampler, scheduler, grounding, and reference-boost defaults; do not send a negative prompt. When Krea is selected, override the generic prompt-length guidance with a concise 1-4 sentence delta instruction; name only the requested change and details that must remain fixed. Put the base scene/image first and an optional person/detail reference second. Z-image, Z-image Turbo, and base Krea 2 Turbo are generate_image img2img models, not edit_image selectors. If the user names another edit/image model, honor it. GPT Image 2 always processes input images at high fidelity; do not set input_fidelity. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
+              "description": "The app auto-selects Fast→Qwen Lightning and HQ/Pro→full Qwen only for ordinary identity-neutral edits. REQUIRED IDENTITY DEFAULT: set \"krea-identity-edit\" whenever an edit of a referenced person or character must keep likeness or character identity while changing clothing, hair or makeup, pose or position, face/head/body, background, lighting, or visual style. Infer that semantic intent in any language; never route from keyword or regex matching. Also use it for a non-Pro single-character sheet. This default applies even when the user did not name Krea; an explicitly requested model always wins. Set \"dark-beast-krea2-identity-edit\" only when the user explicitly requests that model, its uncensored/community variant, or dark_beast_krea2_identity_edit_v1_2. Set \"gpt-image-2\" only when the user explicitly names legacy GPT Image 2 (GPT Image 2, GPT-2, or gpt-image-2); it is never a default. A ChatGPT, OpenAI, GPT, or GPT Image edit request that names no version uses \"gpt-image-2.5-flare\". Set \"gpt-image-2.5-sunburst\" when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets use Sunburst unless the user names another model. If GPT Image 2.5 Sunburst is unavailable for detail-critical layout work, fall back to full \"qwen\", never \"qwen-lightning\". Krea identity edit models require at least one reference image, accept up to two context images, and work best at 512-2048px. Let the model tier and worker choose current steps, guidance, sampler, scheduler, grounding, and reference-boost defaults; do not send a negative prompt. When Krea is selected, override the generic prompt-length guidance with a concise 1-4 sentence delta instruction; name only the requested change and details that must remain fixed. Put the base scene/image first and an optional person/detail reference second. Z-image, Z-image Turbo, and base Krea 2 Turbo are generate_image img2img models, not edit_image selectors. If the user names another edit/image model, honor it. GPT Image 2 always processes input images at high fidelity; do not set input_fidelity. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
             },
             "sourceImageIndex": {
               "type": "number",
@@ -841,7 +842,7 @@
       "type": "function",
       "function": {
         "name": "animate_photo",
-        "description": "Animate a photo into video with motion, audio, and dialogue using LTX 2.5 by default, LTX 2.3 as rollback, or WAN 2.2. Do NOT use this tool for seedance2, seedance2-mini, or seedance2-5. Seedance media references — including Seedance 2.5 first-and-last-frame requests — must go through generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text in the prompt; for seamless-loop Seedance requests with one uploaded image, the prompt should anchor it as both the first frame and last frame. LTX/WAN NOTE: uploaded audio files are not loose references for ltx25/ltx23/wan22; use sound_to_video when uploaded audio is the primary sync target. DANCE REQUESTS (\"make them dance\", \"do the X dance\"): use dance_montage — NOT this tool. LTX 2.5 and LTX 2.3 generate audio natively — describe dialogue and ambient sounds directly in the prompt (do NOT pre-generate audio for this tool). If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Avoid placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. PERSONA PIPELINE: For persona videos, ensure an image of the persona exists before calling animate_photo. The standard pipeline is: resolve_personas → edit_image → animate_photo. If a suitable persona image already exists (user uploaded one, a prior edit_image/generate_image result, OR the user explicitly says to use the Persona image/reference photo directly), skip edit_image and animate directly. After resolve_personas, this tool can animate the injected persona image directly when that explicit direct-use instruction is given. Auto-uses the latest result image (from any prior tool) unless sourceImageIndex is set. Supports start-frame (default), end-frame, and start+end interpolation modes for LTX/WAN — ask the user which frame role their image should play if they mention \"end frame\", \"last frame\", or provide two images. FIRST+LAST FRAME WORKFLOW: When the user wants a non-Seedance video using two different scenes as start and end frames, prefer generating both images in a single generate_image/edit_image call with numberOfVariations=2 and Dynamic Prompts, then call animate_photo with frameRole=\"both\", sourceImageIndex=0, endImageIndex=1. If the user explicitly wants separately created frame assets, preserve that staged instruction while keeping indices correct. In frameRole=\"both\", the handler automatically inspects both images and upgrades the base prompt into a scene-aware smooth transition prompt, so your prompt should state the desired transition style, action, dialogue, and audio rather than trying to list every visible object. If the request is vague, analyze the image first and suggest 2-3 specific animation ideas tailored to what you see. Call once you have clear creative intent. N-VIDEOS PATTERN: Avoid sequential animate_photo calls for N outputs. For a single fixed source/end frame where only prompt text varies, use sourceImageIndex + numberOfVariations=N + one Dynamic Prompt branch in prompt so Sogni submits one project with multiple jobs. If the user explicitly asks for Dynamic Prompt or Dynamic Template syntax, prefer this one-project path whenever every output uses the same source/end frames and shared settings, even if they also ask to stitch the completed clips afterward. Use sourceImageIndices/prompts for multi-segment stitched non-Seedance video, different source/end assets, different audio windows, different durations/dimensions, isolated retry lifecycle, or other per-output parameters. sourceImageIndices supports up to 16 entries; there is NO 3-clip cap, so do not split one planned batch into \"first 3\" and \"remaining\" calls. For a dialogue-heavy total-duration request with no explicit per-clip duration, prefer 15-second clips on ltx25 by default (or ltx23 rollback) (30s total = 2 clips × 15s) and 10-second clips on wan22 (60s total on wan22 = 6 clips × 10s; do NOT pick 4 clips × 15s on wan22 — the wan22 worker rejects clips longer than 10s). Multi-source flavors: (A) SHARED CONTENT — when all N clips have the same dialogue/motion but different source visuals (different scenes, outfits, environments, persona looks), first generate N distinct images via ONE edit_image/generate_image call with numberOfVariations=N + Dynamic Prompts {|}, then call animate_photo with sourceImageIndices=[start..start+N-1] and a single shared `prompt`. If all segments intentionally reuse the primary uploaded image and only prompt text varies, use sourceImageIndex=-1, frameRole=\"both\" if requested, endImageIndex=-1 if requested, numberOfVariations=N, and one Dynamic Prompt branch in prompt. Each branch option must be a complete natural-language motion prompt; do not include \"clip N\", source-frame boilerplate, \"overall request context\", or instructions to follow the user request. For a long scripted/dialogue/storyboard video from a single supplied/uploaded image where each segment needs isolated exact dialogue or per-segment wiring, use sourceImageIndices=[-1,-1,...] and per-clip prompts. Only set frameRole=\"both\" and endImageIndex=-1 when the user explicitly says the same uploaded/source/original image should be both the first and last frame of every segment. If the user requests generated source images first, honor that image stage, then animate the generated result indices. When using generated scene keyframes and each clip should begin and end on its own scene image for stitching, call animate_photo with frameRole=\"both\" and sourceImageIndices=[start..end] but OMIT endImageIndex; do not set endImageIndex=-1 unless every source is the uploaded image. (B) PER-CLIP CONTENT — when source/end asset wiring or other per-output parameters differ, pass BOTH sourceImageIndices AND `prompts` (an array of N strings, one per clip) in the same single call. Each prompt must independently anchor the visible characters, scene action, camera, audio, exact screenplay-style speaker tags, and exact quoted dialogue for that segment. If you just wrote or displayed a script/table, copy the exact dialogue lines into the corresponding per-clip prompts; do not summarize them as speech activity. If using named speaker tags with any multi-person reference image or generated scene keyframe, include one explicit cast map in each prompt that binds each name to visible position, clothing, and props/actions, e.g. SPEAKER_A = left person holding a prop; SPEAKER_B = center person with tablet; SPEAKER_C = right person near table. Do not also describe the same people again as generic man/boy/girl/woman/character subjects. For screenplay, storyboard, commercial, series, or other longer-form tasks with recurring characters, preserve the same character names and repeated visual anchors in every per-clip prompt where each character appears. Use the standard single-source path (numberOfVariations only) when the user wants motion variety from a single fixed frame. Wan 3 first-frame and first+last-frame generation is supported with videoModel=\"wan3.0-video\". Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; it supports first-frame, last-frame-only, and first+last-frame generation, but frame anchors cannot be mixed with loose references.",
+        "description": "Animate a photo into video with motion, audio, and dialogue using LTX 2.5 by default, LTX 2.3 as rollback, or WAN 2.2. Do NOT use this tool for seedance2, seedance2-mini, seedance2-5, or seedance2-5-uncensored. Seedance media references — including Seedance 2.5 first-and-last-frame requests — must go through generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text in the prompt; for seamless-loop Seedance requests with one uploaded image, the prompt should anchor it as both the first frame and last frame. LTX/WAN NOTE: uploaded audio files are not loose references for ltx25/ltx23/wan22; use sound_to_video when uploaded audio is the primary sync target. DANCE REQUESTS (\"make them dance\", \"do the X dance\"): use dance_montage — NOT this tool. LTX 2.5 and LTX 2.3 generate audio natively — describe dialogue and ambient sounds directly in the prompt (do NOT pre-generate audio for this tool). If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Avoid placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. PERSONA PIPELINE: For persona videos, ensure an image of the persona exists before calling animate_photo. The standard pipeline is: resolve_personas → edit_image → animate_photo. If a suitable persona image already exists (user uploaded one, a prior edit_image/generate_image result, OR the user explicitly says to use the Persona image/reference photo directly), skip edit_image and animate directly. After resolve_personas, this tool can animate the injected persona image directly when that explicit direct-use instruction is given. Auto-uses the latest result image (from any prior tool) unless sourceImageIndex is set. Supports start-frame (default), end-frame, and start+end interpolation modes for LTX/WAN — ask the user which frame role their image should play if they mention \"end frame\", \"last frame\", or provide two images. FIRST+LAST FRAME WORKFLOW: When the user wants a non-Seedance video using two different scenes as start and end frames, prefer generating both images in a single generate_image/edit_image call with numberOfVariations=2 and Dynamic Prompts, then call animate_photo with frameRole=\"both\", sourceImageIndex=0, endImageIndex=1. If the user explicitly wants separately created frame assets, preserve that staged instruction while keeping indices correct. In frameRole=\"both\", the handler automatically inspects both images and upgrades the base prompt into a scene-aware smooth transition prompt, so your prompt should state the desired transition style, action, dialogue, and audio rather than trying to list every visible object. If the request is vague, analyze the image first and suggest 2-3 specific animation ideas tailored to what you see. Call once you have clear creative intent. N-VIDEOS PATTERN: Avoid sequential animate_photo calls for N outputs. For a single fixed source/end frame where only prompt text varies, use sourceImageIndex + numberOfVariations=N + one Dynamic Prompt branch in prompt so Sogni submits one project with multiple jobs. If the user explicitly asks for Dynamic Prompt or Dynamic Template syntax, prefer this one-project path whenever every output uses the same source/end frames and shared settings, even if they also ask to stitch the completed clips afterward. Use sourceImageIndices/prompts for multi-segment stitched non-Seedance video, different source/end assets, different audio windows, different durations/dimensions, isolated retry lifecycle, or other per-output parameters. sourceImageIndices supports up to 16 entries; there is NO 3-clip cap, so do not split one planned batch into \"first 3\" and \"remaining\" calls. For a dialogue-heavy total-duration request with no explicit per-clip duration, prefer 15-second clips on ltx25 by default (or ltx23 rollback) (30s total = 2 clips × 15s) and 10-second clips on wan22 (60s total on wan22 = 6 clips × 10s; do NOT pick 4 clips × 15s on wan22 — the wan22 worker rejects clips longer than 10s). Multi-source flavors: (A) SHARED CONTENT — when all N clips have the same dialogue/motion but different source visuals (different scenes, outfits, environments, persona looks), first generate N distinct images via ONE edit_image/generate_image call with numberOfVariations=N + Dynamic Prompts {|}, then call animate_photo with sourceImageIndices=[start..start+N-1] and a single shared `prompt`. If all segments intentionally reuse the primary uploaded image and only prompt text varies, use sourceImageIndex=-1, frameRole=\"both\" if requested, endImageIndex=-1 if requested, numberOfVariations=N, and one Dynamic Prompt branch in prompt. Each branch option must be a complete natural-language motion prompt; do not include \"clip N\", source-frame boilerplate, \"overall request context\", or instructions to follow the user request. For a long scripted/dialogue/storyboard video from a single supplied/uploaded image where each segment needs isolated exact dialogue or per-segment wiring, use sourceImageIndices=[-1,-1,...] and per-clip prompts. Only set frameRole=\"both\" and endImageIndex=-1 when the user explicitly says the same uploaded/source/original image should be both the first and last frame of every segment. If the user requests generated source images first, honor that image stage, then animate the generated result indices. When using generated scene keyframes and each clip should begin and end on its own scene image for stitching, call animate_photo with frameRole=\"both\" and sourceImageIndices=[start..end] but OMIT endImageIndex; do not set endImageIndex=-1 unless every source is the uploaded image. (B) PER-CLIP CONTENT — when source/end asset wiring or other per-output parameters differ, pass BOTH sourceImageIndices AND `prompts` (an array of N strings, one per clip) in the same single call. Each prompt must independently anchor the visible characters, scene action, camera, audio, exact screenplay-style speaker tags, and exact quoted dialogue for that segment. If you just wrote or displayed a script/table, copy the exact dialogue lines into the corresponding per-clip prompts; do not summarize them as speech activity. If using named speaker tags with any multi-person reference image or generated scene keyframe, include one explicit cast map in each prompt that binds each name to visible position, clothing, and props/actions, e.g. SPEAKER_A = left person holding a prop; SPEAKER_B = center person with tablet; SPEAKER_C = right person near table. Do not also describe the same people again as generic man/boy/girl/woman/character subjects. For screenplay, storyboard, commercial, series, or other longer-form tasks with recurring characters, preserve the same character names and repeated visual anchors in every per-clip prompt where each character appears. Use the standard single-source path (numberOfVariations only) when the user wants motion variety from a single fixed frame. Wan 3 first-frame and first+last-frame generation is supported with videoModel=\"wan3.0-video\". Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; it supports first-frame, last-frame-only, and first+last-frame generation, but frame anchors cannot be mixed with loose references.",
         "parameters": {
           "type": "object",
           "properties": {
@@ -1062,7 +1063,7 @@
             },
             "negativePrompt": {
               "type": "string",
-              "description": "Advanced non-Seedance only. Use this field only when the user explicitly asks to set a separate negative prompt. For ordinary avoid/no/don't constraints on LTX 2.3 or WAN 2.2, translate them into affirmative production constraints inside prompt instead; do not move them here. Do not set when controlMode is seedance-v2v or videoModel is seedance2/seedance2-mini/seedance2-5."
+              "description": "Advanced non-Seedance only. Use this field only when the user explicitly asks to set a separate negative prompt. For ordinary avoid/no/don't constraints on LTX 2.3 or WAN 2.2, translate them into affirmative production constraints inside prompt instead; do not move them here. Do not set when controlMode is seedance-v2v or videoModel is seedance2/seedance2-mini/seedance2-5/seedance2-5-uncensored."
             },
             "videoModel": {
               "type": "string",
@@ -1072,9 +1073,10 @@
                 "wan22-animate",
                 "seedance2",
                 "seedance2-mini",
-                "seedance2-5"
+                "seedance2-5",
+                "seedance2-5-uncensored"
               ],
-              "description": "Model selector for this video-to-video request. Usually omit: non-Seedance controls default to \"ltx25-v2v\"; use \"ltx23-v2v\" only for rollback. LTX 2.5 Fast, HQ, and Pro currently use the release-validated official Distilled workflow for canny, pose, depth, detailer, inpaint, and outpaint. Dev is not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. For controlMode=\"seedance-v2v\", Seedance quality is selected only by model: use \"seedance2-mini\" for faster/lower-cost drafts and use \"seedance2\" for full-quality Seedance or 1080p/4K. \"seedance2-5\" supports 480p/720p/1080p, 4-30s at 24 fps, native audio, and first/last-frame conditioning; keep \"seedance2\" for 4K."
+              "description": "Model selector for this video-to-video request. Usually omit: non-Seedance controls default to \"ltx25-v2v\"; use \"ltx23-v2v\" only for rollback. LTX 2.5 Fast, HQ, and Pro currently use the release-validated official Distilled workflow for canny, pose, depth, detailer, inpaint, and outpaint. Dev is not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. For controlMode=\"seedance-v2v\", Seedance quality is selected only by model: use \"seedance2-mini\" for faster/lower-cost drafts and use \"seedance2\" for full-quality Seedance or 1080p/4K. \"seedance2-5\" supports 480p/720p/1080p, 4-30s at 24 fps, native audio, and first/last-frame conditioning; keep \"seedance2\" for 4K. \"seedance2-5-uncensored\": Seedance 2.5 Uncensored — the uncensored variant of Seedance 2.5, with every mode, resolution, duration, reference limit, and output option described for \"seedance2-5\". Choose it only when the user asks for Seedance 2.5 Uncensored (including \"Seedance Uncensored\" or \"Seedance Spicy\") or for uncensored Seedance output; never swap it in for \"seedance2-5\" otherwise. Each account must accept a one-time likeness and consent agreement in the Sogni app before its first render; until then the job fails with error 4103, so tell the user to accept it in the Sogni app instead of retrying."
             },
             "generateAudio": {
               "type": "boolean",
@@ -1082,7 +1084,7 @@
             },
             "targetResolution": {
               "type": "number",
-              "description": "Seedance V2V only. Short-side output resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact dimensions. Seedance V2V full supports 4K; Seedance V2V Mini and Fast support 480p and 720p only; Seedance 2.5 also supports 1080p, so never set 4K for \"seedance2-5\". Preserve the source video shape instead of forcing landscape pixels."
+              "description": "Seedance V2V only. Short-side output resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact dimensions. Seedance V2V full supports 4K; Seedance V2V Mini and Fast support 480p and 720p only; Seedance 2.5 also supports 1080p, so never set 4K for \"seedance2-5\" or \"seedance2-5-uncensored\". Preserve the source video shape instead of forcing landscape pixels."
             },
             "sourceImageIndex": {
               "type": "number",
@@ -1322,7 +1324,7 @@
       "type": "function",
       "function": {
         "name": "sound_to_video",
-        "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx25-ia2v by default (ltx23-ia2v is rollback); for lip-sync with a face image, use wan-s2v; if no image, use ltx25-a2v by default (ltx23-a2v is rollback). If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.5 and LTX 2.3 generate audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video with videoModel=\"ltx23\" because LTX 2.5 has no compatible ID-LoRA. LONG AUDIO ON SEEDANCE: Seedance 2.0 and Mini cap each clip at 15s; Seedance 2.5 renders up to 30s in one call, so prefer seedance2-5 for 16-30s audio instead of splitting. When the user uploads audio longer than the per-clip cap of the selected model and Seedance is selected (seedance2, seedance2-mini, or seedance2-5), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them. Use videoModel=\"wan3.0-video\" when the user explicitly requests Wan 3 audio-driven video. Use videoModel=\"wan3.0-spicy-video\" for Wan 3.0 Enhanced audio-driven video through MuleRouter provider ID w3.0-video; it supports adaptive ratios and provider prompt expansion. MINIMAX H3 AUDIO: only when the user asks for MiniMax H3 or FastH3 audio-driven video, use videoModel=\"minimax-h3-fasth3-ia2v-turbo\" with a first-frame image (sourceImageIndex), \"minimax-h3-fasth3-flfa2v-turbo\" with a first and a last frame (sourceImageIndex and endImageIndex), or \"minimax-h3-fasth3-a2v-turbo\" with no image; add \"-2stage\" only for 1080p, 1440p or 2K H3 output. Without an explicit MiniMax H3 or FastH3 request keep the LTX 2.5 defaults. The MiniMax H3 selectors on generate_video and animate_photo cannot take an uploaded audio track; send uploaded-audio H3 requests here.",
+        "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx25-ia2v by default (ltx23-ia2v is rollback); for lip-sync with a face image, use wan-s2v; if no image, use ltx25-a2v by default (ltx23-a2v is rollback). If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.5 and LTX 2.3 generate audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video with videoModel=\"ltx23\" because LTX 2.5 has no compatible ID-LoRA. LONG AUDIO ON SEEDANCE: Seedance 2.0 and Mini cap each clip at 15s; Seedance 2.5 renders up to 30s in one call, so prefer seedance2-5 for 16-30s audio instead of splitting. When the user uploads audio longer than the per-clip cap of the selected model and Seedance is selected (seedance2, seedance2-mini, seedance2-5, or seedance2-5-uncensored), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them. Use videoModel=\"wan3.0-video\" when the user explicitly requests Wan 3 audio-driven video. Use videoModel=\"wan3.0-spicy-video\" for Wan 3.0 Enhanced audio-driven video through MuleRouter provider ID w3.0-video; it supports adaptive ratios and provider prompt expansion. MINIMAX H3 AUDIO: only when the user asks for MiniMax H3 or FastH3 audio-driven video, use videoModel=\"minimax-h3-fasth3-ia2v-turbo\" with a first-frame image (sourceImageIndex), \"minimax-h3-fasth3-flfa2v-turbo\" with a first and a last frame (sourceImageIndex and endImageIndex), or \"minimax-h3-fasth3-a2v-turbo\" with no image; add \"-2stage\" only for 1080p, 1440p or 2K H3 output. Without an explicit MiniMax H3 or FastH3 request keep the LTX 2.5 defaults. The MiniMax H3 selectors on generate_video and animate_photo cannot take an uploaded audio track; send uploaded-audio H3 requests here.",
         "parameters": {
           "type": "object",
           "properties": {
@@ -1392,6 +1394,7 @@
                 "seedance2",
                 "seedance2-mini",
                 "seedance2-5",
+                "seedance2-5-uncensored",
                 "ltx25-ia2v",
                 "ltx25-a2v",
                 "ltx23-ia2v",
@@ -1405,7 +1408,7 @@
                 "minimax-h3-fasth3-a2v-turbo",
                 "minimax-h3-fasth3-a2v-turbo-2stage"
               ],
-              "description": "\"ltx25-ia2v\" (default with image) and \"ltx25-a2v\" (default without image): LTX 2.5 image+audio and audio-only modes; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflows. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates official ComfyUI Dev recipes. Video model. \"ltx23-ia2v\" (rollback with image): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. \"ltx23-a2v\" (rollback without image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s. \"seedance2-mini\": Seedance 2.0 Mini, 720p cap, fastest/lower-cost Seedance option. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster/lower-cost drafts or explicit Mini requests, and pick \"seedance2\" for full-quality Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension. MiniMax H3 FastH3 audio guide: \"minimax-h3-fasth3-ia2v-turbo\" (first-frame image from sourceImageIndex plus the audio), \"minimax-h3-fasth3-flfa2v-turbo\" (first frame from sourceImageIndex, last frame from endImageIndex, plus the audio) and \"minimax-h3-fasth3-a2v-turbo\" (audio only; set neither sourceImageIndex nor endImageIndex) run the four-step FastH3 engine with the uploaded audio driving the picture from frame 0, and the output keeps that audio as its soundtrack. Choose them only when the user asks for MiniMax H3 or FastH3; never pick them in place of the LTX 2.5 defaults. They render 124-362 frames on the H3 17-frame grid at a fixed 24 fps (about 5.2-15.1 seconds) on a 32px grid within 1344x768, so use targetResolution 768 or omit it. audioStart picks the window of the upload. MiniMax H3 catalog and Personal LoRAs are supported across audio modes and tiers. generateAudio=false and negativePrompt are not supported. Each costs the FastH3 price of its image-to-video, first-and-last-frame or text-to-video mode, 4 Spark per second. \"minimax-h3-fasth3-ia2v-turbo-2stage\", \"minimax-h3-fasth3-flfa2v-turbo-2stage\" and \"minimax-h3-fasth3-a2v-turbo-2stage\" are the two-stage forms: the same inputs rendered on the FastH3 canvas, then enlarged 2x and refined, delivered at twice the canvas with the same length and audio. For them targetResolution names the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, and 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second. The audio two-stage selectors have no 720p price class (720 would render a 384px canvas at the 1080p rate), so for 720p or 768p audio-guided H3 output use the regular selector. The estimate prices every request."
+              "description": "\"ltx25-ia2v\" (default with image) and \"ltx25-a2v\" (default without image): LTX 2.5 image+audio and audio-only modes; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflows. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates official ComfyUI Dev recipes. Video model. \"ltx23-ia2v\" (rollback with image): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. \"ltx23-a2v\" (rollback without image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s. \"seedance2-mini\": Seedance 2.0 Mini, 720p cap, fastest/lower-cost Seedance option. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster/lower-cost drafts or explicit Mini requests, and pick \"seedance2\" for full-quality Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. \"seedance2-5-uncensored\": Seedance 2.5 Uncensored — the uncensored variant of Seedance 2.5, with every mode, resolution, duration, reference limit, and output option described for \"seedance2-5\". Choose it only when the user asks for Seedance 2.5 Uncensored (including \"Seedance Uncensored\" or \"Seedance Spicy\") or for uncensored Seedance output; never swap it in for \"seedance2-5\" otherwise. Each account must accept a one-time likeness and consent agreement in the Sogni app before its first render; until then the job fails with error 4103, so tell the user to accept it in the Sogni app instead of retrying. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension. MiniMax H3 FastH3 audio guide: \"minimax-h3-fasth3-ia2v-turbo\" (first-frame image from sourceImageIndex plus the audio), \"minimax-h3-fasth3-flfa2v-turbo\" (first frame from sourceImageIndex, last frame from endImageIndex, plus the audio) and \"minimax-h3-fasth3-a2v-turbo\" (audio only; set neither sourceImageIndex nor endImageIndex) run the four-step FastH3 engine with the uploaded audio driving the picture from frame 0, and the output keeps that audio as its soundtrack. Choose them only when the user asks for MiniMax H3 or FastH3; never pick them in place of the LTX 2.5 defaults. They render 124-362 frames on the H3 17-frame grid at a fixed 24 fps (about 5.2-15.1 seconds) on a 32px grid within 1344x768, so use targetResolution 768 or omit it. audioStart picks the window of the upload. MiniMax H3 catalog and Personal LoRAs are supported across audio modes and tiers. generateAudio=false and negativePrompt are not supported. Each costs the FastH3 price of its image-to-video, first-and-last-frame or text-to-video mode, 4 Spark per second. \"minimax-h3-fasth3-ia2v-turbo-2stage\", \"minimax-h3-fasth3-flfa2v-turbo-2stage\" and \"minimax-h3-fasth3-a2v-turbo-2stage\" are the two-stage forms: the same inputs rendered on the FastH3 canvas, then enlarged 2x and refined, delivered at twice the canvas with the same length and audio. For them targetResolution names the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, and 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second. The audio two-stage selectors have no 720p price class (720 would render a 384px canvas at the 1080p rate), so for 720p or 768p audio-guided H3 output use the regular selector. The estimate prices every request."
             },
             "generateAudio": {
               "type": "boolean",
@@ -1493,7 +1496,8 @@
                 "ltx23",
                 "seedance2",
                 "seedance2-mini",
-                "seedance2-5"
+                "seedance2-5",
+                "seedance2-5-uncensored"
               ],
               "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance for a Seedance base and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. Override only when the user explicitly requests a different model."
             },
@@ -1555,7 +1559,8 @@
                 "wan22",
                 "seedance2",
                 "seedance2-mini",
-                "seedance2-5"
+                "seedance2-5",
+                "seedance2-5-uncensored"
               ],
               "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance or WAN for matching base clips and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. Override only when the user explicitly requests a different model."
             },

package/manifests/openai-tools.json

@@ -46,7 +46,7 @@
                 "pony-faetality",
                 "dreamshaper-xl"
               ],
-              "description": "DO NOT SET THIS PARAMETER unless the user names a specific model, asks for a very complex image render, asks for a video storyboard/storyboard sheet/contact sheet/panel layout image, asks for anime without naming a model, requests permitted NSFW/nudity content, or explicitly asks for Z-image/Z-image Turbo/Krea 2 Turbo image-to-image. The app auto-selects based on quality settings. Set \"gpt-image-2\" when the user explicitly asks for legacy GPT Image 2. Set \"gpt-image-2.5-sunburst\" by default for complex single-image renders that need very strong text rendering, dense labels, crisp typography, multi-panel composition, timing notes, foley notes, professional storyboard-sheet layout, or a comprehensive character/mascot/model sheet with turnarounds, expressions, accessories, palette swatches, and brand notes. Set \"one-obsession-v22\" when the user asks for an anime or anime-style image and has not named a specific image model. Set \"z-turbo\" when the user asks for Z-image Turbo; set \"z-image\" when they ask for Z-image without Turbo. Set \"krea-2-turbo\" when the user asks for Krea 2 Turbo. If the user names another image model, honor that requested model instead. A model preference usually does not change which tool to use; the Z-image and Krea 2 Turbo image-to-image exception uses sourceImageIndex plus starting_image_strength on this tool. NSFW rule: \"gpt-image-2\"/Qwen image models CANNOT do nudity. For permitted NSFW/nudity content, prefer \"dark-beast-krea2\", then \"dark-beast-z-turbo\"; \"chroma1-hd\", \"pony-v7\", \"chroma-detail\", \"chroma-v46-flash\", and \"z-turbo\" are compatible fallbacks. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
+              "description": "DO NOT SET THIS PARAMETER unless the user names a specific model, asks for a very complex image render, asks for a video storyboard/storyboard sheet/contact sheet/panel layout image, asks for anime without naming a model, requests permitted NSFW/nudity content, or explicitly asks for Z-image/Z-image Turbo/Krea 2 Turbo image-to-image. The app auto-selects based on quality settings. Set \"gpt-image-2.5-flare\" when the user asks for a ChatGPT, OpenAI, GPT, or GPT Image image/model without naming a version. Set \"gpt-image-2\" only when the user explicitly names GPT Image 2, GPT-2, or gpt-image-2; GPT Image 2 is never a default. Set \"gpt-image-2.5-sunburst\" when the user explicitly requests very strong text rendering, and by default for video storyboards and other complex single-image renders that need dense labels, crisp typography, multi-panel composition, timing notes, foley notes, professional storyboard-sheet layout, or a comprehensive character/mascot/model sheet with turnarounds, expressions, accessories, palette swatches, and brand notes. Set \"one-obsession-v22\" when the user asks for an anime or anime-style image and has not named a specific image model. Set \"z-turbo\" when the user asks for Z-image Turbo; set \"z-image\" when they ask for Z-image without Turbo. Set \"krea-2-turbo\" when the user asks for Krea 2 Turbo. If the user names another image model, honor that requested model instead. A model preference usually does not change which tool to use; the Z-image and Krea 2 Turbo image-to-image exception uses sourceImageIndex plus starting_image_strength on this tool. NSFW rule: GPT Image models and Qwen image models CANNOT do nudity. For permitted NSFW/nudity content, prefer \"dark-beast-krea2\", then \"dark-beast-z-turbo\"; \"chroma1-hd\", \"pony-v7\", \"chroma-detail\", \"chroma-v46-flash\", and \"z-turbo\" are compatible fallbacks. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
             },
             "width": {
               "type": "number",
@@ -152,7 +152,7 @@
       "type": "function",
       "function": {
         "name": "generate_video",
-        "description": "Generate a video from text or Seedance multimodal references. LTX 2.5 is the default and generates audio natively; LTX 2.3 remains available as rollback and also generates audio natively (dialogue, sounds, ambient music) — describe audio in the prompt. If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Never use placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. For non-Seedance syncing to a specific song or audio track, use sound_to_video instead. For non-Seedance animation from a locked source photo, use animate_photo. Do NOT use for My Personas unless generating a Seedance reference-based video — standard persona videos use resolve_personas → edit_image → animate_photo. SEEDANCE DEFAULT: For seedance2, seedance2-mini, or seedance2-5, default to exactly one video (4-15s on 2.0/Mini, 4-30s on seedance2-5) unless the user explicitly asks for multiple separate outputs. Multiple beats, shots, or scene descriptions in one up-to-15s Seedance prompt are still one video. If the user requests one continuous Seedance video longer than 15s, prefer seedance2-5, which renders up to 30s in a single call; beyond 30s (or on 2.0/Mini) preserve the requested total duration in the prompt/context and let chat orchestration split it into supported segment renders and stitch them instead of clamping it to a short excerpt. Uploaded/generated storyboard, shot-sheet, or trailer-concept images used as Seedance references should become one Seedance 2.5 generate_video call at targetResolution=1080 by default; preserve an explicitly requested model or resolution, and use Seedance 2.0 for 4K because Seedance 2.5 supports up to 1080p. Do not extract panels with edit_image and do not animate the storyboard sheet with LTX unless the user explicitly asks for separate non-Seedance clips. Seedance loose image, video, and audio references go through this tool; do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. If the uploaded audio is the primary sync target, lip-sync target, or requested as sound-to-video/audio-sync, use sound_to_video with videoModel=\"seedance2-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render and audit the composite board, generate one scene reference still per approved scene with GPT Image 2.5 Sunburst, render each scene as a Seedance 2.5 video segment at targetResolution=1080, then stitch the segments. Preserve an explicit alternate model or resolution. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent. WAN 3 uses the exact selector wan3.0-video: use this tool for text-to-video or loose Image 1/Video 1/Audio 1 references; use animate_photo for native first/last frames and sound_to_video when audio drives timing. A Wan 3 video reference conditions a new generation; it does not invoke a provider-backed edit or extend mode. Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; use this tool for prompt-only or loose-reference generation, and never combine loose references with frame anchors.",
+        "description": "Generate a video from text or Seedance multimodal references. LTX 2.5 is the default and generates audio natively; LTX 2.3 remains available as rollback and also generates audio natively (dialogue, sounds, ambient music) — describe audio in the prompt. If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Never use placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. For non-Seedance syncing to a specific song or audio track, use sound_to_video instead. For non-Seedance animation from a locked source photo, use animate_photo. Do NOT use for My Personas unless generating a Seedance reference-based video — standard persona videos use resolve_personas → edit_image → animate_photo. SEEDANCE DEFAULT: For seedance2, seedance2-mini, seedance2-5, or seedance2-5-uncensored, default to exactly one video (4-15s on 2.0/Mini, 4-30s on seedance2-5 and seedance2-5-uncensored) unless the user explicitly asks for multiple separate outputs. Multiple beats, shots, or scene descriptions in one up-to-15s Seedance prompt are still one video. If the user requests one continuous Seedance video longer than 15s, prefer seedance2-5, which renders up to 30s in a single call; beyond 30s (or on 2.0/Mini) preserve the requested total duration in the prompt/context and let chat orchestration split it into supported segment renders and stitch them instead of clamping it to a short excerpt. Uploaded/generated storyboard, shot-sheet, or trailer-concept images used as Seedance references should become one Seedance 2.5 generate_video call at targetResolution=1080 by default; preserve an explicitly requested model or resolution, and use Seedance 2.0 for 4K because Seedance 2.5 supports up to 1080p. Do not extract panels with edit_image and do not animate the storyboard sheet with LTX unless the user explicitly asks for separate non-Seedance clips. Seedance loose image, video, and audio references go through this tool; do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. If the uploaded audio is the primary sync target, lip-sync target, or requested as sound-to-video/audio-sync, use sound_to_video with videoModel=\"seedance2-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render and audit the composite board, generate one scene reference still per approved scene with GPT Image 2.5 Sunburst, render each scene as a Seedance 2.5 video segment at targetResolution=1080, then stitch the segments. Preserve an explicit alternate model or resolution. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent. WAN 3 uses the exact selector wan3.0-video: use this tool for text-to-video or loose Image 1/Video 1/Audio 1 references; use animate_photo for native first/last frames and sound_to_video when audio drives timing. A Wan 3 video reference conditions a new generation; it does not invoke a provider-backed edit or extend mode. Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; use this tool for prompt-only or loose-reference generation, and never combine loose references with frame anchors.",
         "parameters": {
           "type": "object",
           "properties": {
@@ -211,6 +211,7 @@
                 "seedance2",
                 "seedance2-mini",
                 "seedance2-5",
+                "seedance2-5-uncensored",
                 "minimax-h3-t2v",
                 "minimax-h3-t2v-turbo",
                 "minimax-h3-fasth3-t2v-turbo",
@@ -225,7 +226,7 @@
                 "wan3.0-video",
                 "wan3.0-spicy-video"
               ],
-              "description": "\"ltx25\" (default): LTX 2.5 with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Video model. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio. \"minimax-h3-t2v\": standard 20-step MiniMax H3 text-to-video; \"minimax-h3-t2v-turbo\": the existing 4-step LightX2V Turbo text-to-video; \"minimax-h3-fasth3-t2v-turbo\": the separate FastVideo VSA four-step FastH3 engine, about 2x faster and fixed to Euler/simple; \"minimax-h3-fasth3-t2v-turbo-2stage\": the two-stage FastH3 engine: FastH3 renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length and audio. targetResolution picks the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second, and 720 renders a 384px canvas (672x384 is delivered at 1344x768) for the regular FastH3 price of 4 Spark per second. The estimate prices every request. It takes the same inputs, durations and LoRAs as \"minimax-h3-fasth3-t2v-turbo\". Choose it when the user asks for 1080p, 1440p or 2K MiniMax H3 output, for two-stage output, or for the sharpest/best H3 quality; for ordinary 768p FastH3 output keep the regular FastH3 selector at targetResolution 768. All use native audio, fixed 24fps, 5.17-15.08s, and a 768p-class 32px-grid canvas; use animate_photo for H3 image-conditioned modes. Base and Turbo T2V/I2V/FLF2V prompts use the exact ordered fields integrated_multimodal_description, overall_soundscape, and non_diegetic_music; I2V/FLF2V prepend the official alignment line. \"minimax-h3-r2v\": standard 20-step MiniMax H3 reference-to-video; \"minimax-h3-r2v-turbo\": the dedicated LightX2V 4-step Ref2VA Turbo workflow using Euler/simple and a 960x544 default. \"minimax-h3-r2v-2stage\" (Standard, 20 steps, res_multistep/simple) and \"minimax-h3-r2v-balanced-2stage\" (Balanced, 8 steps, Euler/simple) are the two-stage reference-to-video forms: the tier renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length, audio and references. targetResolution names the delivered class exactly as for the FastH3 two-stage selectors: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088), 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536), and 720 renders a 384px canvas (672x384 is delivered at 1344x768). Each bills its tier's own per-second rate plus the two-stage surcharge of the delivered class (none at 720p); the estimate prices every request. Choose one when the user asks for 1080p, 1440p or 2K MiniMax H3 reference-to-video output; keep the one-stage \"minimax-h3-r2v\" or Balanced selector for ordinary 768p output. FastH3 has no R2V mode. Every R2V selector accepts up to 9 images, 3 videos, and 3 audios (12 files total); at least one visual reference (image or video) is required and audio alone is invalid. Select references with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and address them with the official <Subject N>/<Picture N>/<Video N>/<Audio N> semantics. Seedance quality is selected only by model: use \"seedance2-mini\" for Seedance 2.0 Mini or faster/lower-cost 720p iteration, use \"seedance2-5\" at targetResolution=1080 for generated/uploaded storyboard images and current high-quality Seedance generation unless the user explicitly requests another model or resolution, and use \"seedance2\" for Seedance 2.0 or 4K requests because Seedance 2.5 supports up to 1080p. Do not use Default Media Quality Fast/HQ/Pro to represent Seedance quality. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. Seedance supports multimodal loose reference assets. Seedance 2.0 and Mini accept up to 9 images, 3 videos, and 3 audios, with no more than 12 asset files total. Seedance 2.5 accepts up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Use @Image1/@Video1/@Audio1 style references in creative briefs when assigning roles. Assign every useful reference asset a role and prefer positive preservation constraints. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. Alibaba HappyHorse 1.1 video models (third-party vendor — requires Premium Spark). Select by mode: \"happyhorse-1.1-t2v\" for text-to-video, \"happyhorse-1.1-i2v\" for image-to-video from one first-frame image, and \"happyhorse-1.1-r2v\" for reference-to-video with up to 9 reference images. Resolutions 720P and 1080P; duration 3-15 seconds at 24 fps; native synchronized audio is always generated (do not set generateAudio or negativePrompt). Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9. HappyHorse 1.1 takes image references only and renders a native synchronized audio track (always on; do not set generateAudio or a negative prompt). Pick the model by mode: happyhorse-1.1-t2v for text-to-video (no reference image), happyhorse-1.1-i2v for image-to-video from a single first frame, and happyhorse-1.1-r2v for reference-to-video with 1 to 9 reference images. For r2v, tag the images in the prompt as [Image 1]…[Image 9] and assign each a clear role. HappyHorse does not accept reference videos or reference audios. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension."
+              "description": "\"ltx25\" (default): LTX 2.5 with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Video model. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio. \"minimax-h3-t2v\": standard 20-step MiniMax H3 text-to-video; \"minimax-h3-t2v-turbo\": the existing 4-step LightX2V Turbo text-to-video; \"minimax-h3-fasth3-t2v-turbo\": the separate FastVideo VSA four-step FastH3 engine, about 2x faster and fixed to Euler/simple; \"minimax-h3-fasth3-t2v-turbo-2stage\": the two-stage FastH3 engine: FastH3 renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length and audio. targetResolution picks the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second, and 720 renders a 384px canvas (672x384 is delivered at 1344x768) for the regular FastH3 price of 4 Spark per second. The estimate prices every request. It takes the same inputs, durations and LoRAs as \"minimax-h3-fasth3-t2v-turbo\". Choose it when the user asks for 1080p, 1440p or 2K MiniMax H3 output, for two-stage output, or for the sharpest/best H3 quality; for ordinary 768p FastH3 output keep the regular FastH3 selector at targetResolution 768. All use native audio, fixed 24fps, 5.17-15.08s, and a 768p-class 32px-grid canvas; use animate_photo for H3 image-conditioned modes. Base and Turbo T2V/I2V/FLF2V prompts use the exact ordered fields integrated_multimodal_description, overall_soundscape, and non_diegetic_music; I2V/FLF2V prepend the official alignment line. \"minimax-h3-r2v\": standard 20-step MiniMax H3 reference-to-video; \"minimax-h3-r2v-turbo\": the dedicated LightX2V 4-step Ref2VA Turbo workflow using Euler/simple and a 960x544 default. \"minimax-h3-r2v-2stage\" (Standard, 20 steps, res_multistep/simple) and \"minimax-h3-r2v-balanced-2stage\" (Balanced, 8 steps, Euler/simple) are the two-stage reference-to-video forms: the tier renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length, audio and references. targetResolution names the delivered class exactly as for the FastH3 two-stage selectors: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088), 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536), and 720 renders a 384px canvas (672x384 is delivered at 1344x768). Each bills its tier's own per-second rate plus the two-stage surcharge of the delivered class (none at 720p); the estimate prices every request. Choose one when the user asks for 1080p, 1440p or 2K MiniMax H3 reference-to-video output; keep the one-stage \"minimax-h3-r2v\" or Balanced selector for ordinary 768p output. FastH3 has no R2V mode. Every R2V selector accepts up to 9 images, 3 videos, and 3 audios (12 files total); at least one visual reference (image or video) is required and audio alone is invalid. Select references with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and address them with the official <Subject N>/<Picture N>/<Video N>/<Audio N> semantics. Seedance quality is selected only by model: use \"seedance2-mini\" for Seedance 2.0 Mini or faster/lower-cost 720p iteration, use \"seedance2-5\" at targetResolution=1080 for generated/uploaded storyboard images and current high-quality Seedance generation unless the user explicitly requests another model or resolution, and use \"seedance2\" for Seedance 2.0 or 4K requests because Seedance 2.5 supports up to 1080p. Do not use Default Media Quality Fast/HQ/Pro to represent Seedance quality. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. \"seedance2-5-uncensored\": Seedance 2.5 Uncensored — the uncensored variant of Seedance 2.5, with every mode, resolution, duration, reference limit, and output option described for \"seedance2-5\". Choose it only when the user asks for Seedance 2.5 Uncensored (including \"Seedance Uncensored\" or \"Seedance Spicy\") or for uncensored Seedance output; never swap it in for \"seedance2-5\" otherwise. Each account must accept a one-time likeness and consent agreement in the Sogni app before its first render; until then the job fails with error 4103, so tell the user to accept it in the Sogni app instead of retrying. Seedance supports multimodal loose reference assets. Seedance 2.0 and Mini accept up to 9 images, 3 videos, and 3 audios, with no more than 12 asset files total. Seedance 2.5 accepts up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Use @Image1/@Video1/@Audio1 style references in creative briefs when assigning roles. Assign every useful reference asset a role and prefer positive preservation constraints. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. Alibaba HappyHorse 1.1 video models (third-party vendor — requires Premium Spark). Select by mode: \"happyhorse-1.1-t2v\" for text-to-video, \"happyhorse-1.1-i2v\" for image-to-video from one first-frame image, and \"happyhorse-1.1-r2v\" for reference-to-video with up to 9 reference images. Resolutions 720P and 1080P; duration 3-15 seconds at 24 fps; native synchronized audio is always generated (do not set generateAudio or negativePrompt). Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9. HappyHorse 1.1 takes image references only and renders a native synchronized audio track (always on; do not set generateAudio or a negative prompt). Pick the model by mode: happyhorse-1.1-t2v for text-to-video (no reference image), happyhorse-1.1-i2v for image-to-video from a single first frame, and happyhorse-1.1-r2v for reference-to-video with 1 to 9 reference images. For r2v, tag the images in the prompt as [Image 1]…[Image 9] and assign each a clear role. HappyHorse does not accept reference videos or reference audios. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension."
             },
             "generateAudio": {
               "type": "boolean",
@@ -262,7 +263,7 @@
             },
             "targetResolution": {
               "type": "number",
-              "description": "Short-side video resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact pixels or an output orientation. This is resolution only, not a Seedance quality tier: Seedance quality is selected by videoModel (\"seedance2\" vs \"seedance2-mini\" vs \"seedance2-5\"). Seedance 2.0 full supports 4K; Seedance Mini supports 480p/720p; Seedance 2.5 supports 480p/720p/1080p, so never set 4K for \"seedance2-5\". Wan 3 supports exactly 480p, 720p, and 1080p. HappyHorse supports only 720p and 1080p. Never set 4K for Wan 3 or HappyHorse. MiniMax H3 renders inside a 1344x768 pixel budget on a 32px grid, so use 768 for the regular H3 selectors and never 1080p or 4K. The two-stage H3 selector \"minimax-h3-fasth3-t2v-turbo-2stage\" delivers twice the canvas, so there targetResolution names the delivered short-edge class: 1080 (544px canvas short edge: 960x544 delivered at 1920x1088), 1440 for 2K (the 1344x768 canvas delivered at 2688x1536), or 720 (384px canvas: 672x384 delivered at 1344x768); omit it for 2K. Never set 4K for H3. Do not set targetResolution from Default Media Quality Fast/HQ/Pro. If omitted for Seedance, Wan 3, HappyHorse, or MiniMax H3, the host uses the selected model default. This preserves/inherits the current video shape instead of forcing landscape. Do NOT set width, height, or exact-pixel aspectRatio for bare named resolution requests. If the user says \"720p portrait\", \"720p landscape\", \"4K portrait\", or \"4K landscape\", use exact width/height/aspectRatio instead."
+              "description": "Short-side video resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact pixels or an output orientation. This is resolution only, not a Seedance quality tier: Seedance quality is selected by videoModel (\"seedance2\" vs \"seedance2-mini\" vs \"seedance2-5\"). Seedance 2.0 full supports 4K; Seedance Mini supports 480p/720p; Seedance 2.5 supports 480p/720p/1080p, so never set 4K for \"seedance2-5\" or \"seedance2-5-uncensored\". Wan 3 supports exactly 480p, 720p, and 1080p. HappyHorse supports only 720p and 1080p. Never set 4K for Wan 3 or HappyHorse. MiniMax H3 renders inside a 1344x768 pixel budget on a 32px grid, so use 768 for the regular H3 selectors and never 1080p or 4K. The two-stage H3 selector \"minimax-h3-fasth3-t2v-turbo-2stage\" delivers twice the canvas, so there targetResolution names the delivered short-edge class: 1080 (544px canvas short edge: 960x544 delivered at 1920x1088), 1440 for 2K (the 1344x768 canvas delivered at 2688x1536), or 720 (384px canvas: 672x384 delivered at 1344x768); omit it for 2K. Never set 4K for H3. Do not set targetResolution from Default Media Quality Fast/HQ/Pro. If omitted for Seedance, Wan 3, HappyHorse, or MiniMax H3, the host uses the selected model default. This preserves/inherits the current video shape instead of forcing landscape. Do NOT set width, height, or exact-pixel aspectRatio for bare named resolution requests. If the user says \"720p portrait\", \"720p landscape\", \"4K portrait\", or \"4K landscape\", use exact width/height/aspectRatio instead."
             },
             "numberOfVariations": {
               "type": "number",
@@ -509,7 +510,7 @@
                 "krea-identity-edit",
                 "dark-beast-krea2-identity-edit"
               ],
-              "description": "The app auto-selects Fast→Qwen Lightning and HQ/Pro→full Qwen only for ordinary identity-neutral edits. REQUIRED IDENTITY DEFAULT: set \"krea-identity-edit\" whenever an edit of a referenced person or character must keep likeness or character identity while changing clothing, hair or makeup, pose or position, face/head/body, background, lighting, or visual style. Infer that semantic intent in any language; never route from keyword or regex matching. Also use it for a non-Pro single-character sheet. This default applies even when the user did not name Krea; an explicitly requested model always wins. Set \"dark-beast-krea2-identity-edit\" only when the user explicitly requests that model, its uncensored/community variant, or dark_beast_krea2_identity_edit_v1_2. Set \"gpt-image-2\" when the user explicitly names legacy GPT Image 2. Set \"gpt-image-2.5-sunburst\" when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets may use Sunburst. If GPT Image 2.5 Sunburst is unavailable for detail-critical layout work, fall back to full \"qwen\", never \"qwen-lightning\". Krea identity edit models require at least one reference image, accept up to two context images, and work best at 512-2048px. Let the model tier and worker choose current steps, guidance, sampler, scheduler, grounding, and reference-boost defaults; do not send a negative prompt. When Krea is selected, override the generic prompt-length guidance with a concise 1-4 sentence delta instruction; name only the requested change and details that must remain fixed. Put the base scene/image first and an optional person/detail reference second. Z-image, Z-image Turbo, and base Krea 2 Turbo are generate_image img2img models, not edit_image selectors. If the user names another edit/image model, honor it. GPT Image 2 always processes input images at high fidelity; do not set input_fidelity. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
+              "description": "The app auto-selects Fast→Qwen Lightning and HQ/Pro→full Qwen only for ordinary identity-neutral edits. REQUIRED IDENTITY DEFAULT: set \"krea-identity-edit\" whenever an edit of a referenced person or character must keep likeness or character identity while changing clothing, hair or makeup, pose or position, face/head/body, background, lighting, or visual style. Infer that semantic intent in any language; never route from keyword or regex matching. Also use it for a non-Pro single-character sheet. This default applies even when the user did not name Krea; an explicitly requested model always wins. Set \"dark-beast-krea2-identity-edit\" only when the user explicitly requests that model, its uncensored/community variant, or dark_beast_krea2_identity_edit_v1_2. Set \"gpt-image-2\" only when the user explicitly names legacy GPT Image 2 (GPT Image 2, GPT-2, or gpt-image-2); it is never a default. A ChatGPT, OpenAI, GPT, or GPT Image edit request that names no version uses \"gpt-image-2.5-flare\". Set \"gpt-image-2.5-sunburst\" when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets use Sunburst unless the user names another model. If GPT Image 2.5 Sunburst is unavailable for detail-critical layout work, fall back to full \"qwen\", never \"qwen-lightning\". Krea identity edit models require at least one reference image, accept up to two context images, and work best at 512-2048px. Let the model tier and worker choose current steps, guidance, sampler, scheduler, grounding, and reference-boost defaults; do not send a negative prompt. When Krea is selected, override the generic prompt-length guidance with a concise 1-4 sentence delta instruction; name only the requested change and details that must remain fixed. Put the base scene/image first and an optional person/detail reference second. Z-image, Z-image Turbo, and base Krea 2 Turbo are generate_image img2img models, not edit_image selectors. If the user names another edit/image model, honor it. GPT Image 2 always processes input images at high fidelity; do not set input_fidelity. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
             },
             "sourceImageIndex": {
               "type": "number",
@@ -816,7 +817,7 @@
       "type": "function",
       "function": {
         "name": "animate_photo",
-        "description": "Animate a photo into video with motion, audio, and dialogue using LTX 2.5 by default, LTX 2.3 as rollback, or WAN 2.2. Do NOT use this tool for seedance2, seedance2-mini, or seedance2-5. Seedance media references — including Seedance 2.5 first-and-last-frame requests — must go through generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text in the prompt; for seamless-loop Seedance requests with one uploaded image, the prompt should anchor it as both the first frame and last frame. LTX/WAN NOTE: uploaded audio files are not loose references for ltx25/ltx23/wan22; use sound_to_video when uploaded audio is the primary sync target. DANCE REQUESTS (\"make them dance\", \"do the X dance\"): use dance_montage — NOT this tool. LTX 2.5 and LTX 2.3 generate audio natively — describe dialogue and ambient sounds directly in the prompt (do NOT pre-generate audio for this tool). If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Avoid placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. PERSONA PIPELINE: For persona videos, ensure an image of the persona exists before calling animate_photo. The standard pipeline is: resolve_personas → edit_image → animate_photo. If a suitable persona image already exists (user uploaded one, a prior edit_image/generate_image result, OR the user explicitly says to use the Persona image/reference photo directly), skip edit_image and animate directly. After resolve_personas, this tool can animate the injected persona image directly when that explicit direct-use instruction is given. Auto-uses the latest result image (from any prior tool) unless sourceImageIndex is set. Supports start-frame (default), end-frame, and start+end interpolation modes for LTX/WAN — ask the user which frame role their image should play if they mention \"end frame\", \"last frame\", or provide two images. FIRST+LAST FRAME WORKFLOW: When the user wants a non-Seedance video using two different scenes as start and end frames, prefer generating both images in a single generate_image/edit_image call with numberOfVariations=2 and Dynamic Prompts, then call animate_photo with frameRole=\"both\", sourceImageIndex=0, endImageIndex=1. If the user explicitly wants separately created frame assets, preserve that staged instruction while keeping indices correct. In frameRole=\"both\", the handler automatically inspects both images and upgrades the base prompt into a scene-aware smooth transition prompt, so your prompt should state the desired transition style, action, dialogue, and audio rather than trying to list every visible object. If the request is vague, analyze the image first and suggest 2-3 specific animation ideas tailored to what you see. Call once you have clear creative intent. N-VIDEOS PATTERN: Avoid sequential animate_photo calls for N outputs. For a single fixed source/end frame where only prompt text varies, use sourceImageIndex + numberOfVariations=N + one Dynamic Prompt branch in prompt so Sogni submits one project with multiple jobs. If the user explicitly asks for Dynamic Prompt or Dynamic Template syntax, prefer this one-project path whenever every output uses the same source/end frames and shared settings, even if they also ask to stitch the completed clips afterward. Use sourceImageIndices/prompts for multi-segment stitched non-Seedance video, different source/end assets, different audio windows, different durations/dimensions, isolated retry lifecycle, or other per-output parameters. sourceImageIndices supports up to 16 entries; there is NO 3-clip cap, so do not split one planned batch into \"first 3\" and \"remaining\" calls. For a dialogue-heavy total-duration request with no explicit per-clip duration, prefer 15-second clips on ltx25 by default (or ltx23 rollback) (30s total = 2 clips × 15s) and 10-second clips on wan22 (60s total on wan22 = 6 clips × 10s; do NOT pick 4 clips × 15s on wan22 — the wan22 worker rejects clips longer than 10s). Multi-source flavors: (A) SHARED CONTENT — when all N clips have the same dialogue/motion but different source visuals (different scenes, outfits, environments, persona looks), first generate N distinct images via ONE edit_image/generate_image call with numberOfVariations=N + Dynamic Prompts {|}, then call animate_photo with sourceImageIndices=[start..start+N-1] and a single shared `prompt`. If all segments intentionally reuse the primary uploaded image and only prompt text varies, use sourceImageIndex=-1, frameRole=\"both\" if requested, endImageIndex=-1 if requested, numberOfVariations=N, and one Dynamic Prompt branch in prompt. Each branch option must be a complete natural-language motion prompt; do not include \"clip N\", source-frame boilerplate, \"overall request context\", or instructions to follow the user request. For a long scripted/dialogue/storyboard video from a single supplied/uploaded image where each segment needs isolated exact dialogue or per-segment wiring, use sourceImageIndices=[-1,-1,...] and per-clip prompts. Only set frameRole=\"both\" and endImageIndex=-1 when the user explicitly says the same uploaded/source/original image should be both the first and last frame of every segment. If the user requests generated source images first, honor that image stage, then animate the generated result indices. When using generated scene keyframes and each clip should begin and end on its own scene image for stitching, call animate_photo with frameRole=\"both\" and sourceImageIndices=[start..end] but OMIT endImageIndex; do not set endImageIndex=-1 unless every source is the uploaded image. (B) PER-CLIP CONTENT — when source/end asset wiring or other per-output parameters differ, pass BOTH sourceImageIndices AND `prompts` (an array of N strings, one per clip) in the same single call. Each prompt must independently anchor the visible characters, scene action, camera, audio, exact screenplay-style speaker tags, and exact quoted dialogue for that segment. If you just wrote or displayed a script/table, copy the exact dialogue lines into the corresponding per-clip prompts; do not summarize them as speech activity. If using named speaker tags with any multi-person reference image or generated scene keyframe, include one explicit cast map in each prompt that binds each name to visible position, clothing, and props/actions, e.g. SPEAKER_A = left person holding a prop; SPEAKER_B = center person with tablet; SPEAKER_C = right person near table. Do not also describe the same people again as generic man/boy/girl/woman/character subjects. For screenplay, storyboard, commercial, series, or other longer-form tasks with recurring characters, preserve the same character names and repeated visual anchors in every per-clip prompt where each character appears. Use the standard single-source path (numberOfVariations only) when the user wants motion variety from a single fixed frame. Wan 3 first-frame and first+last-frame generation is supported with videoModel=\"wan3.0-video\". Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; it supports first-frame, last-frame-only, and first+last-frame generation, but frame anchors cannot be mixed with loose references.",
+        "description": "Animate a photo into video with motion, audio, and dialogue using LTX 2.5 by default, LTX 2.3 as rollback, or WAN 2.2. Do NOT use this tool for seedance2, seedance2-mini, seedance2-5, or seedance2-5-uncensored. Seedance media references — including Seedance 2.5 first-and-last-frame requests — must go through generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text in the prompt; for seamless-loop Seedance requests with one uploaded image, the prompt should anchor it as both the first frame and last frame. LTX/WAN NOTE: uploaded audio files are not loose references for ltx25/ltx23/wan22; use sound_to_video when uploaded audio is the primary sync target. DANCE REQUESTS (\"make them dance\", \"do the X dance\"): use dance_montage — NOT this tool. LTX 2.5 and LTX 2.3 generate audio natively — describe dialogue and ambient sounds directly in the prompt (do NOT pre-generate audio for this tool). If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Avoid placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. PERSONA PIPELINE: For persona videos, ensure an image of the persona exists before calling animate_photo. The standard pipeline is: resolve_personas → edit_image → animate_photo. If a suitable persona image already exists (user uploaded one, a prior edit_image/generate_image result, OR the user explicitly says to use the Persona image/reference photo directly), skip edit_image and animate directly. After resolve_personas, this tool can animate the injected persona image directly when that explicit direct-use instruction is given. Auto-uses the latest result image (from any prior tool) unless sourceImageIndex is set. Supports start-frame (default), end-frame, and start+end interpolation modes for LTX/WAN — ask the user which frame role their image should play if they mention \"end frame\", \"last frame\", or provide two images. FIRST+LAST FRAME WORKFLOW: When the user wants a non-Seedance video using two different scenes as start and end frames, prefer generating both images in a single generate_image/edit_image call with numberOfVariations=2 and Dynamic Prompts, then call animate_photo with frameRole=\"both\", sourceImageIndex=0, endImageIndex=1. If the user explicitly wants separately created frame assets, preserve that staged instruction while keeping indices correct. In frameRole=\"both\", the handler automatically inspects both images and upgrades the base prompt into a scene-aware smooth transition prompt, so your prompt should state the desired transition style, action, dialogue, and audio rather than trying to list every visible object. If the request is vague, analyze the image first and suggest 2-3 specific animation ideas tailored to what you see. Call once you have clear creative intent. N-VIDEOS PATTERN: Avoid sequential animate_photo calls for N outputs. For a single fixed source/end frame where only prompt text varies, use sourceImageIndex + numberOfVariations=N + one Dynamic Prompt branch in prompt so Sogni submits one project with multiple jobs. If the user explicitly asks for Dynamic Prompt or Dynamic Template syntax, prefer this one-project path whenever every output uses the same source/end frames and shared settings, even if they also ask to stitch the completed clips afterward. Use sourceImageIndices/prompts for multi-segment stitched non-Seedance video, different source/end assets, different audio windows, different durations/dimensions, isolated retry lifecycle, or other per-output parameters. sourceImageIndices supports up to 16 entries; there is NO 3-clip cap, so do not split one planned batch into \"first 3\" and \"remaining\" calls. For a dialogue-heavy total-duration request with no explicit per-clip duration, prefer 15-second clips on ltx25 by default (or ltx23 rollback) (30s total = 2 clips × 15s) and 10-second clips on wan22 (60s total on wan22 = 6 clips × 10s; do NOT pick 4 clips × 15s on wan22 — the wan22 worker rejects clips longer than 10s). Multi-source flavors: (A) SHARED CONTENT — when all N clips have the same dialogue/motion but different source visuals (different scenes, outfits, environments, persona looks), first generate N distinct images via ONE edit_image/generate_image call with numberOfVariations=N + Dynamic Prompts {|}, then call animate_photo with sourceImageIndices=[start..start+N-1] and a single shared `prompt`. If all segments intentionally reuse the primary uploaded image and only prompt text varies, use sourceImageIndex=-1, frameRole=\"both\" if requested, endImageIndex=-1 if requested, numberOfVariations=N, and one Dynamic Prompt branch in prompt. Each branch option must be a complete natural-language motion prompt; do not include \"clip N\", source-frame boilerplate, \"overall request context\", or instructions to follow the user request. For a long scripted/dialogue/storyboard video from a single supplied/uploaded image where each segment needs isolated exact dialogue or per-segment wiring, use sourceImageIndices=[-1,-1,...] and per-clip prompts. Only set frameRole=\"both\" and endImageIndex=-1 when the user explicitly says the same uploaded/source/original image should be both the first and last frame of every segment. If the user requests generated source images first, honor that image stage, then animate the generated result indices. When using generated scene keyframes and each clip should begin and end on its own scene image for stitching, call animate_photo with frameRole=\"both\" and sourceImageIndices=[start..end] but OMIT endImageIndex; do not set endImageIndex=-1 unless every source is the uploaded image. (B) PER-CLIP CONTENT — when source/end asset wiring or other per-output parameters differ, pass BOTH sourceImageIndices AND `prompts` (an array of N strings, one per clip) in the same single call. Each prompt must independently anchor the visible characters, scene action, camera, audio, exact screenplay-style speaker tags, and exact quoted dialogue for that segment. If you just wrote or displayed a script/table, copy the exact dialogue lines into the corresponding per-clip prompts; do not summarize them as speech activity. If using named speaker tags with any multi-person reference image or generated scene keyframe, include one explicit cast map in each prompt that binds each name to visible position, clothing, and props/actions, e.g. SPEAKER_A = left person holding a prop; SPEAKER_B = center person with tablet; SPEAKER_C = right person near table. Do not also describe the same people again as generic man/boy/girl/woman/character subjects. For screenplay, storyboard, commercial, series, or other longer-form tasks with recurring characters, preserve the same character names and repeated visual anchors in every per-clip prompt where each character appears. Use the standard single-source path (numberOfVariations only) when the user wants motion variety from a single fixed frame. Wan 3 first-frame and first+last-frame generation is supported with videoModel=\"wan3.0-video\". Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; it supports first-frame, last-frame-only, and first+last-frame generation, but frame anchors cannot be mixed with loose references.",
         "parameters": {
           "type": "object",
           "properties": {
@@ -1037,7 +1038,7 @@
             },
             "negativePrompt": {
               "type": "string",
-              "description": "Advanced non-Seedance only. Use this field only when the user explicitly asks to set a separate negative prompt. For ordinary avoid/no/don't constraints on LTX 2.3 or WAN 2.2, translate them into affirmative production constraints inside prompt instead; do not move them here. Do not set when controlMode is seedance-v2v or videoModel is seedance2/seedance2-mini/seedance2-5."
+              "description": "Advanced non-Seedance only. Use this field only when the user explicitly asks to set a separate negative prompt. For ordinary avoid/no/don't constraints on LTX 2.3 or WAN 2.2, translate them into affirmative production constraints inside prompt instead; do not move them here. Do not set when controlMode is seedance-v2v or videoModel is seedance2/seedance2-mini/seedance2-5/seedance2-5-uncensored."
             },
             "videoModel": {
               "type": "string",
@@ -1047,9 +1048,10 @@
                 "wan22-animate",
                 "seedance2",
                 "seedance2-mini",
-                "seedance2-5"
+                "seedance2-5",
+                "seedance2-5-uncensored"
               ],
-              "description": "Model selector for this video-to-video request. Usually omit: non-Seedance controls default to \"ltx25-v2v\"; use \"ltx23-v2v\" only for rollback. LTX 2.5 Fast, HQ, and Pro currently use the release-validated official Distilled workflow for canny, pose, depth, detailer, inpaint, and outpaint. Dev is not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. For controlMode=\"seedance-v2v\", Seedance quality is selected only by model: use \"seedance2-mini\" for faster/lower-cost drafts and use \"seedance2\" for full-quality Seedance or 1080p/4K. \"seedance2-5\" supports 480p/720p/1080p, 4-30s at 24 fps, native audio, and first/last-frame conditioning; keep \"seedance2\" for 4K."
+              "description": "Model selector for this video-to-video request. Usually omit: non-Seedance controls default to \"ltx25-v2v\"; use \"ltx23-v2v\" only for rollback. LTX 2.5 Fast, HQ, and Pro currently use the release-validated official Distilled workflow for canny, pose, depth, detailer, inpaint, and outpaint. Dev is not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. For controlMode=\"seedance-v2v\", Seedance quality is selected only by model: use \"seedance2-mini\" for faster/lower-cost drafts and use \"seedance2\" for full-quality Seedance or 1080p/4K. \"seedance2-5\" supports 480p/720p/1080p, 4-30s at 24 fps, native audio, and first/last-frame conditioning; keep \"seedance2\" for 4K. \"seedance2-5-uncensored\": Seedance 2.5 Uncensored — the uncensored variant of Seedance 2.5, with every mode, resolution, duration, reference limit, and output option described for \"seedance2-5\". Choose it only when the user asks for Seedance 2.5 Uncensored (including \"Seedance Uncensored\" or \"Seedance Spicy\") or for uncensored Seedance output; never swap it in for \"seedance2-5\" otherwise. Each account must accept a one-time likeness and consent agreement in the Sogni app before its first render; until then the job fails with error 4103, so tell the user to accept it in the Sogni app instead of retrying."
             },
             "generateAudio": {
               "type": "boolean",
@@ -1057,7 +1059,7 @@
             },
             "targetResolution": {
               "type": "number",
-              "description": "Seedance V2V only. Short-side output resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact dimensions. Seedance V2V full supports 4K; Seedance V2V Mini and Fast support 480p and 720p only; Seedance 2.5 also supports 1080p, so never set 4K for \"seedance2-5\". Preserve the source video shape instead of forcing landscape pixels."
+              "description": "Seedance V2V only. Short-side output resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact dimensions. Seedance V2V full supports 4K; Seedance V2V Mini and Fast support 480p and 720p only; Seedance 2.5 also supports 1080p, so never set 4K for \"seedance2-5\" or \"seedance2-5-uncensored\". Preserve the source video shape instead of forcing landscape pixels."
             },
             "sourceImageIndex": {
               "type": "number",
@@ -1297,7 +1299,7 @@
       "type": "function",
       "function": {
         "name": "sound_to_video",
-        "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx25-ia2v by default (ltx23-ia2v is rollback); for lip-sync with a face image, use wan-s2v; if no image, use ltx25-a2v by default (ltx23-a2v is rollback). If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.5 and LTX 2.3 generate audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video with videoModel=\"ltx23\" because LTX 2.5 has no compatible ID-LoRA. LONG AUDIO ON SEEDANCE: Seedance 2.0 and Mini cap each clip at 15s; Seedance 2.5 renders up to 30s in one call, so prefer seedance2-5 for 16-30s audio instead of splitting. When the user uploads audio longer than the per-clip cap of the selected model and Seedance is selected (seedance2, seedance2-mini, or seedance2-5), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them. Use videoModel=\"wan3.0-video\" when the user explicitly requests Wan 3 audio-driven video. Use videoModel=\"wan3.0-spicy-video\" for Wan 3.0 Enhanced audio-driven video through MuleRouter provider ID w3.0-video; it supports adaptive ratios and provider prompt expansion. MINIMAX H3 AUDIO: only when the user asks for MiniMax H3 or FastH3 audio-driven video, use videoModel=\"minimax-h3-fasth3-ia2v-turbo\" with a first-frame image (sourceImageIndex), \"minimax-h3-fasth3-flfa2v-turbo\" with a first and a last frame (sourceImageIndex and endImageIndex), or \"minimax-h3-fasth3-a2v-turbo\" with no image; add \"-2stage\" only for 1080p, 1440p or 2K H3 output. Without an explicit MiniMax H3 or FastH3 request keep the LTX 2.5 defaults. The MiniMax H3 selectors on generate_video and animate_photo cannot take an uploaded audio track; send uploaded-audio H3 requests here.",
+        "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx25-ia2v by default (ltx23-ia2v is rollback); for lip-sync with a face image, use wan-s2v; if no image, use ltx25-a2v by default (ltx23-a2v is rollback). If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.5 and LTX 2.3 generate audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video with videoModel=\"ltx23\" because LTX 2.5 has no compatible ID-LoRA. LONG AUDIO ON SEEDANCE: Seedance 2.0 and Mini cap each clip at 15s; Seedance 2.5 renders up to 30s in one call, so prefer seedance2-5 for 16-30s audio instead of splitting. When the user uploads audio longer than the per-clip cap of the selected model and Seedance is selected (seedance2, seedance2-mini, seedance2-5, or seedance2-5-uncensored), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them. Use videoModel=\"wan3.0-video\" when the user explicitly requests Wan 3 audio-driven video. Use videoModel=\"wan3.0-spicy-video\" for Wan 3.0 Enhanced audio-driven video through MuleRouter provider ID w3.0-video; it supports adaptive ratios and provider prompt expansion. MINIMAX H3 AUDIO: only when the user asks for MiniMax H3 or FastH3 audio-driven video, use videoModel=\"minimax-h3-fasth3-ia2v-turbo\" with a first-frame image (sourceImageIndex), \"minimax-h3-fasth3-flfa2v-turbo\" with a first and a last frame (sourceImageIndex and endImageIndex), or \"minimax-h3-fasth3-a2v-turbo\" with no image; add \"-2stage\" only for 1080p, 1440p or 2K H3 output. Without an explicit MiniMax H3 or FastH3 request keep the LTX 2.5 defaults. The MiniMax H3 selectors on generate_video and animate_photo cannot take an uploaded audio track; send uploaded-audio H3 requests here.",
         "parameters": {
           "type": "object",
           "properties": {
@@ -1367,6 +1369,7 @@
                 "seedance2",
                 "seedance2-mini",
                 "seedance2-5",
+                "seedance2-5-uncensored",
                 "ltx25-ia2v",
                 "ltx25-a2v",
                 "ltx23-ia2v",
@@ -1380,7 +1383,7 @@
                 "minimax-h3-fasth3-a2v-turbo",
                 "minimax-h3-fasth3-a2v-turbo-2stage"
               ],
-              "description": "\"ltx25-ia2v\" (default with image) and \"ltx25-a2v\" (default without image): LTX 2.5 image+audio and audio-only modes; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflows. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates official ComfyUI Dev recipes. Video model. \"ltx23-ia2v\" (rollback with image): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. \"ltx23-a2v\" (rollback without image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s. \"seedance2-mini\": Seedance 2.0 Mini, 720p cap, fastest/lower-cost Seedance option. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster/lower-cost drafts or explicit Mini requests, and pick \"seedance2\" for full-quality Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension. MiniMax H3 FastH3 audio guide: \"minimax-h3-fasth3-ia2v-turbo\" (first-frame image from sourceImageIndex plus the audio), \"minimax-h3-fasth3-flfa2v-turbo\" (first frame from sourceImageIndex, last frame from endImageIndex, plus the audio) and \"minimax-h3-fasth3-a2v-turbo\" (audio only; set neither sourceImageIndex nor endImageIndex) run the four-step FastH3 engine with the uploaded audio driving the picture from frame 0, and the output keeps that audio as its soundtrack. Choose them only when the user asks for MiniMax H3 or FastH3; never pick them in place of the LTX 2.5 defaults. They render 124-362 frames on the H3 17-frame grid at a fixed 24 fps (about 5.2-15.1 seconds) on a 32px grid within 1344x768, so use targetResolution 768 or omit it. audioStart picks the window of the upload. MiniMax H3 catalog and Personal LoRAs are supported across audio modes and tiers. generateAudio=false and negativePrompt are not supported. Each costs the FastH3 price of its image-to-video, first-and-last-frame or text-to-video mode, 4 Spark per second. \"minimax-h3-fasth3-ia2v-turbo-2stage\", \"minimax-h3-fasth3-flfa2v-turbo-2stage\" and \"minimax-h3-fasth3-a2v-turbo-2stage\" are the two-stage forms: the same inputs rendered on the FastH3 canvas, then enlarged 2x and refined, delivered at twice the canvas with the same length and audio. For them targetResolution names the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, and 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second. The audio two-stage selectors have no 720p price class (720 would render a 384px canvas at the 1080p rate), so for 720p or 768p audio-guided H3 output use the regular selector. The estimate prices every request."
+              "description": "\"ltx25-ia2v\" (default with image) and \"ltx25-a2v\" (default without image): LTX 2.5 image+audio and audio-only modes; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflows. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates official ComfyUI Dev recipes. Video model. \"ltx23-ia2v\" (rollback with image): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. \"ltx23-a2v\" (rollback without image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s. \"seedance2-mini\": Seedance 2.0 Mini, 720p cap, fastest/lower-cost Seedance option. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster/lower-cost drafts or explicit Mini requests, and pick \"seedance2\" for full-quality Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. \"seedance2-5-uncensored\": Seedance 2.5 Uncensored — the uncensored variant of Seedance 2.5, with every mode, resolution, duration, reference limit, and output option described for \"seedance2-5\". Choose it only when the user asks for Seedance 2.5 Uncensored (including \"Seedance Uncensored\" or \"Seedance Spicy\") or for uncensored Seedance output; never swap it in for \"seedance2-5\" otherwise. Each account must accept a one-time likeness and consent agreement in the Sogni app before its first render; until then the job fails with error 4103, so tell the user to accept it in the Sogni app instead of retrying. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension. MiniMax H3 FastH3 audio guide: \"minimax-h3-fasth3-ia2v-turbo\" (first-frame image from sourceImageIndex plus the audio), \"minimax-h3-fasth3-flfa2v-turbo\" (first frame from sourceImageIndex, last frame from endImageIndex, plus the audio) and \"minimax-h3-fasth3-a2v-turbo\" (audio only; set neither sourceImageIndex nor endImageIndex) run the four-step FastH3 engine with the uploaded audio driving the picture from frame 0, and the output keeps that audio as its soundtrack. Choose them only when the user asks for MiniMax H3 or FastH3; never pick them in place of the LTX 2.5 defaults. They render 124-362 frames on the H3 17-frame grid at a fixed 24 fps (about 5.2-15.1 seconds) on a 32px grid within 1344x768, so use targetResolution 768 or omit it. audioStart picks the window of the upload. MiniMax H3 catalog and Personal LoRAs are supported across audio modes and tiers. generateAudio=false and negativePrompt are not supported. Each costs the FastH3 price of its image-to-video, first-and-last-frame or text-to-video mode, 4 Spark per second. \"minimax-h3-fasth3-ia2v-turbo-2stage\", \"minimax-h3-fasth3-flfa2v-turbo-2stage\" and \"minimax-h3-fasth3-a2v-turbo-2stage\" are the two-stage forms: the same inputs rendered on the FastH3 canvas, then enlarged 2x and refined, delivered at twice the canvas with the same length and audio. For them targetResolution names the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, and 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second. The audio two-stage selectors have no 720p price class (720 would render a 384px canvas at the 1080p rate), so for 720p or 768p audio-guided H3 output use the regular selector. The estimate prices every request."
             },
             "generateAudio": {
               "type": "boolean",
@@ -1468,9 +1471,10 @@
                 "ltx23",
                 "seedance2",
                 "seedance2-mini",
-                "seedance2-5"
+                "seedance2-5",
+                "seedance2-5-uncensored"
               ],
-              "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance for a Seedance base and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. \"seedance2-5\" supports 480p/720p and 4-30s of new footage at 24 fps."
+              "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance for a Seedance base and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. \"seedance2-5\" and \"seedance2-5-uncensored\" (Seedance 2.5 Uncensored, only when requested) support 480p/720p and 4-30s of new footage at 24 fps."
             },
             "keepOriginalAudio": {
               "type": "boolean",
@@ -1530,9 +1534,10 @@
                 "wan22",
                 "seedance2",
                 "seedance2-mini",
-                "seedance2-5"
+                "seedance2-5",
+                "seedance2-5-uncensored"
               ],
-              "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance or WAN for matching base clips and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. \"seedance2-5\" supports 480p/720p and 4-30s replacement windows at 24 fps."
+              "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance or WAN for matching base clips and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. \"seedance2-5\" and \"seedance2-5-uncensored\" (Seedance 2.5 Uncensored, only when requested) support 480p/720p and 4-30s replacement windows at 24 fps."
             },
             "keepOriginalAudio": {
               "type": "boolean",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sogni-ai/sogni-protocol",
-  "version": "1.0.0-alpha.47",
+  "version": "1.0.0-alpha.49",
   "description": "Language-neutral protocol artifacts for the Sogni ecosystem: tool schemas, prompts, OpenAI tool manifests, and enums. Consumed by every Sogni SDK (TypeScript, Swift, and future Python/Kotlin/Rust SDKs) so contracts stay in lockstep across languages.",
   "keywords": [
     "sogni",

package/prompts/tools/edit_image.json

@@ -2,7 +2,7 @@
   "contractId": "edit_image_v1",
   "version": "1.1.0",
   "toolName": "edit_image",
-  "baseDescription": "edit_image applies instruction-based edits to uploaded or generated images. Use when\nuploaded or reference images must guide identity or likeness.\n\nImage-to-Image prompt order: [IDENTITY LOCK] → [REQUESTED EDIT] → [REFERENCE ROLE\nMAPPING] → [POSE/COMPOSITION] → [STYLE] → [LIGHTING/REALISM] → [PRESERVE ALL\nUNMENTIONED DETAILS]. GOLDEN RULE: When editing a person, always state which image owns\nidentity — never leave identity ambiguous. Describe only the DELTA — what changes. Don't\nrewrite the entire image; the base image already contains most of the truth. Default to minimal\nchange. For multi-image edits, assign ONE primary role per reference image (identity, pose,\noutfit, style, environment). Never let a style/pose/clothing reference silently override the face.\nUse positive constraints — \"preserve exact facial likeness, face structure, eye shape, nose\nshape, mouth shape, jawline, skin tone, hairline, apparent age, and overall recognizability\"\n— not vague negatives like \"don't mess up the face\".\n\nUPLOADED IMAGE VARIANT SETS: When the user supplies a photo/portrait/reference image and\nasks for N distinct generated images deriving from that source while changing paired\nper-output details, call edit_image exactly once with sourceImageIndex=-1,\nnumberOfVariations=N, and ONE Dynamic Prompt branch with N complete options. Each option\nmust be a full concrete image prompt for one output, including the uploaded subject/reference\nanchor, requested pose or placement preservation, the specific changed appearance/style/role,\nclothing or surface details when relevant, setting/background, and any requested label text or\nvisual symbol. If one option is a remade original/preserved source and the rest are themed\nvariants, the original option must explicitly say to preserve the original clothing/wardrobe/outfit\nand background/setting, plus any requested added label, flag, logo, symbol, or prop.\nDo not call generate_image, analyze_image, or multiple serial edit_image calls first.\n\nSELECTION-GATED IMAGE STAGES: If the user asks for N image options and says they will pick\none before a later dance/video/animation, call edit_image exactly once with numberOfVariations=N\nand one Dynamic Prompt branch. After images are created, stop and ask the user to choose;\ndo not call dance_montage, animate_photo, or generate_video until they select.\n\nMULTI-PERSONA (COMBINED): When multiple personas must appear in the SAME scene, make\nONE edit_image call with ALL persona faces in one prompt and DO NOT pass personaName.\nPer-persona splits (one call each with personaName set) are RARE — only when the user\nexplicitly asks for solo images of each person individually.\n\nSTORYBOARD IMAGE BATCH RULE: When rendering scene keyframes from a screenplay/storyboard,\nnumberOfVariations is only the count; the prompt MUST be one Dynamic Prompt branch with one\nfull keyframe prompt per scene:\n{scene 1 full keyframe prompt|scene 2 full keyframe prompt|...|scene N full keyframe prompt}.\nNEVER set numberOfVariations=N with only the first scene prompt — that creates N versions of\nscene 1. For full project requests, one edit_image batch for all scene keyframes, then one\nanimate_photo batch for all video clips in parallel.\nException: if the storyboard/shot sheet is already uploaded and the user asks to make a\ntrailer/video/movie/clip from that uploaded board, do not extract panels or redraw keyframes.\nUse generate_video with Seedance references for one continuous clip unless the user explicitly\nasks for separate image keyframes or a storyboard sheet output.\n\nDIRECT UPLOADED GPT IMAGE 2 STORYBOARD SHEETS: If the user uploaded reference images and\nasks for one finished GPT Image 2 storyboard/keyframe sheet now, call edit_image directly\nwith sourceImageIndex=-1, model=\"gpt-image-2\", numberOfVariations=1, and the requested\ncanvas/aspect settings. If the user did not explicitly specify a storyboard page/canvas/sheet\nshape, default the GPT Image 2 storyboard sheet pixel dimensions to a balanced grid that hosts\nthe target cell aspect ratio natively (e.g., 12 cells with 9:16 portrait video target -> ~3:4\nportrait sheet around 1728x2304; 12 cells with 16:9 landscape video target -> ~4:3 landscape\nsheet around 2304x1728; 6 cells with 9:16 target -> ~27:32 portrait sheet around 1840x2176). Do\nNOT default the sheet to 2560x1440 landscape when cells are portrait — a landscape sheet with\na portrait-cell grid physically forces cells to ~4:3 landscape and the model will not render\n9:16 portrait rectangles inside it. Keep individual scene-cell/frame areas at the target video\naspect ratio. Do not call map_assets_for_model, analyze_image, generate_image, or a separate\nplanning tool first. The uploaded files are already available as references; describe their\nroles plainly in the edit_image prompt and generate the sheet in that call.\n\nDO NOT USE edit_image FOR UPLOADED REFERENCE LOOPED VIDEO SEGMENTS: If the user says the\nsame uploaded image/reference should be reused as the first frame and last frame of each\nscripted segment/scene/clip before stitching, they are explicitly asking to animate the\nuploaded image, not to generate new storyboard keyframes. Do not call edit_image for that\nrequest. Call animate_photo once with repeated uploaded source indices and per-scene prompts.\n\nKREA IDENTITY EDIT: Use model=\"krea-identity-edit\" whenever an edit of a referenced person or character must keep likeness or character identity while changing clothing, hair or makeup, pose or position, face/head/body, background, lighting, or visual style. Infer that semantic intent in any language; never route from keyword or regex matching. Also use it for a non-Pro single-character sheet. This default applies even when the user did not name Krea; an explicitly requested model always wins. Use model=\"dark-beast-krea2-identity-edit\" only when the user explicitly requests that model, its uncensored/community variant, or dark_beast_krea2_identity_edit_v1_2. These models require one reference image, accept up to two context images, and work best at 512-2048 px. Let the current model tier and worker choose steps, guidance, sampler, scheduler, grounding, and reference-boost defaults; do not send a negative prompt. Put the primary scene/base image first and an optional person/detail reference second. Write a concise 1-4 sentence delta instruction rather than restating the whole image; reference context_image_0 and context_image_1 when model_ref tokens are needed.\n\nGPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality.",
+  "baseDescription": "edit_image applies instruction-based edits to uploaded or generated images. Use when\nuploaded or reference images must guide identity or likeness.\n\nImage-to-Image prompt order: [IDENTITY LOCK] → [REQUESTED EDIT] → [REFERENCE ROLE\nMAPPING] → [POSE/COMPOSITION] → [STYLE] → [LIGHTING/REALISM] → [PRESERVE ALL\nUNMENTIONED DETAILS]. GOLDEN RULE: When editing a person, always state which image owns\nidentity — never leave identity ambiguous. Describe only the DELTA — what changes. Don't\nrewrite the entire image; the base image already contains most of the truth. Default to minimal\nchange. For multi-image edits, assign ONE primary role per reference image (identity, pose,\noutfit, style, environment). Never let a style/pose/clothing reference silently override the face.\nUse positive constraints — \"preserve exact facial likeness, face structure, eye shape, nose\nshape, mouth shape, jawline, skin tone, hairline, apparent age, and overall recognizability\"\n— not vague negatives like \"don't mess up the face\".\n\nUPLOADED IMAGE VARIANT SETS: When the user supplies a photo/portrait/reference image and\nasks for N distinct generated images deriving from that source while changing paired\nper-output details, call edit_image exactly once with sourceImageIndex=-1,\nnumberOfVariations=N, and ONE Dynamic Prompt branch with N complete options. Each option\nmust be a full concrete image prompt for one output, including the uploaded subject/reference\nanchor, requested pose or placement preservation, the specific changed appearance/style/role,\nclothing or surface details when relevant, setting/background, and any requested label text or\nvisual symbol. If one option is a remade original/preserved source and the rest are themed\nvariants, the original option must explicitly say to preserve the original clothing/wardrobe/outfit\nand background/setting, plus any requested added label, flag, logo, symbol, or prop.\nDo not call generate_image, analyze_image, or multiple serial edit_image calls first.\n\nSELECTION-GATED IMAGE STAGES: If the user asks for N image options and says they will pick\none before a later dance/video/animation, call edit_image exactly once with numberOfVariations=N\nand one Dynamic Prompt branch. After images are created, stop and ask the user to choose;\ndo not call dance_montage, animate_photo, or generate_video until they select.\n\nMULTI-PERSONA (COMBINED): When multiple personas must appear in the SAME scene, make\nONE edit_image call with ALL persona faces in one prompt and DO NOT pass personaName.\nPer-persona splits (one call each with personaName set) are RARE — only when the user\nexplicitly asks for solo images of each person individually.\n\nSTORYBOARD IMAGE BATCH RULE: When rendering scene keyframes from a screenplay/storyboard,\nnumberOfVariations is only the count; the prompt MUST be one Dynamic Prompt branch with one\nfull keyframe prompt per scene:\n{scene 1 full keyframe prompt|scene 2 full keyframe prompt|...|scene N full keyframe prompt}.\nNEVER set numberOfVariations=N with only the first scene prompt — that creates N versions of\nscene 1. For full project requests, one edit_image batch for all scene keyframes, then one\nanimate_photo batch for all video clips in parallel.\nException: if the storyboard/shot sheet is already uploaded and the user asks to make a\ntrailer/video/movie/clip from that uploaded board, do not extract panels or redraw keyframes.\nUse generate_video with Seedance references for one continuous clip unless the user explicitly\nasks for separate image keyframes or a storyboard sheet output.\n\nDIRECT UPLOADED GPT IMAGE STORYBOARD SHEETS: If the user uploaded reference images and\nasks for one finished GPT Image storyboard/keyframe sheet now, call edit_image directly\nwith sourceImageIndex=-1, model=\"gpt-image-2.5-sunburst\", numberOfVariations=1, and the requested\ncanvas/aspect settings. Preserve another explicit GPT Image model named by the user.\nIf the user did not explicitly specify a storyboard page/canvas/sheet\nshape, default the GPT Image 2 storyboard sheet pixel dimensions to a balanced grid that hosts\nthe target cell aspect ratio natively (e.g., 12 cells with 9:16 portrait video target -> ~3:4\nportrait sheet around 1728x2304; 12 cells with 16:9 landscape video target -> ~4:3 landscape\nsheet around 2304x1728; 6 cells with 9:16 target -> ~27:32 portrait sheet around 1840x2176). Do\nNOT default the sheet to 2560x1440 landscape when cells are portrait — a landscape sheet with\na portrait-cell grid physically forces cells to ~4:3 landscape and the model will not render\n9:16 portrait rectangles inside it. Keep individual scene-cell/frame areas at the target video\naspect ratio. Do not call map_assets_for_model, analyze_image, generate_image, or a separate\nplanning tool first. The uploaded files are already available as references; describe their\nroles plainly in the edit_image prompt and generate the sheet in that call.\n\nDO NOT USE edit_image FOR UPLOADED REFERENCE LOOPED VIDEO SEGMENTS: If the user says the\nsame uploaded image/reference should be reused as the first frame and last frame of each\nscripted segment/scene/clip before stitching, they are explicitly asking to animate the\nuploaded image, not to generate new storyboard keyframes. Do not call edit_image for that\nrequest. Call animate_photo once with repeated uploaded source indices and per-scene prompts.\n\nKREA IDENTITY EDIT: Use model=\"krea-identity-edit\" whenever an edit of a referenced person or character must keep likeness or character identity while changing clothing, hair or makeup, pose or position, face/head/body, background, lighting, or visual style. Infer that semantic intent in any language; never route from keyword or regex matching. Also use it for a non-Pro single-character sheet. This default applies even when the user did not name Krea; an explicitly requested model always wins. Use model=\"dark-beast-krea2-identity-edit\" only when the user explicitly requests that model, its uncensored/community variant, or dark_beast_krea2_identity_edit_v1_2. These models require one reference image, accept up to two context images, and work best at 512-2048 px. Let the current model tier and worker choose steps, guidance, sampler, scheduler, grounding, and reference-boost defaults; do not send a negative prompt. Put the primary scene/base image first and an optional person/detail reference second. Write a concise 1-4 sentence delta instruction rather than restating the whole image; reference context_image_0 and context_image_1 when model_ref tokens are needed.\n\nGPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality.",
   "parameterDocs": {
     "sourceImageIndex": "Index of uploaded/generated image. Use -1 for the first uploaded image.",
     "numberOfVariations": "Number of output variants. When > 1, use a Dynamic Prompt branch with one complete prompt per output.",

package/prompts/tools/generate_image.json

@@ -2,7 +2,7 @@
   "contractId": "generate_image_v1",
   "version": "1.2.0",
   "toolName": "generate_image",
-  "baseDescription": "generate_image creates images from text descriptions. Use for text-only image generation;\nuse edit_image when uploaded or reference images must guide identity/likeness.\nException: Z-image and Z-image Turbo image-to-image/enhancement requests use generate_image\nwith model=\"z-turbo\" or model=\"z-image\", sourceImageIndex=-1, and starting_image_strength;\ndo not route explicit Z-image Turbo uploaded-image enhancement to edit_image because\nedit_image does not expose Z-image models.\n\nIMAGE PROMPT ORDER: [SUBJECT] → [ATTRIBUTES] → [ACTION/POSE] → [CAMERA/FRAMING]\n→ [ENVIRONMENT] → [LIGHTING] → [STYLE/MEDIUM] → [MATERIALS/TEXTURES] →\n[SECONDARY DETAILS]. Always start with the main subject, never mood or atmosphere.\nUse concrete nouns and observable adjectives — \"soft overcast daylight\" not \"nice lighting\".\nGood defaults when user is underspecified: medium shot for portraits, wide shot for\nenvironments, eye-level angle, soft natural light for realism.\n\nDYNAMIC PROMPTS: When numberOfVariations > 1, use Dynamic Prompt syntax to make each\nvariation meaningfully different — not just seed-different. Syntax: {a|b|c} cycles\nsequentially, {@a|b|c} picks randomly, {~a|b} paired cycling across groups. Rules: (1) Vary\nONLY what the user left unspecified — lock in everything they specified. (2) Match option\ncount to numberOfVariations so every result is unique. (3) Briefly tell the user what you're\nvarying — never show raw {|} syntax. (4) Skip when: user wants consistency, prompt is fully\nspecified, user typed their own {|} syntax, or iterating on a specific result. (5) NEVER put\nthe count or the word \"versions\"/\"variations\" inside the prompt — the prompt always describes\na single image. The multiplicity comes ONLY from numberOfVariations + the {|} syntax.\nLINKED VARIANTS: when multiple attributes must stay paired per result, use ONE top-level\nDynamic Prompt branch with one complete self-contained prompt per output. Do NOT split\nlinked fields into separate Dynamic Prompt groups.\n\nSELECTION-GATED IMAGE STAGES: If the user asks for N image options and says they will pick\none before a later dance/video/animation, call generate_image once with numberOfVariations=N.\nAfter images are created, stop and ask the user to choose; do not call dance_montage,\nanimate_photo, or generate_video until they select.\n\nIMAGE→VIDEO DIMENSION RULE: When generating an image that will feed into a video tool\n(animate_photo, sound_to_video, etc.), the image MUST be generated at the SAME aspect\nratio and dimensions as the target video. Default video aspect ratio is 16:9 landscape —\npass aspectRatio=\"16:9\" (or the user's specified/reference ratio) so the source image\nmatches the video output. Never generate a square image for a widescreen video. Exception:\na composite GPT Image 2 storyboard/keyframe sheet for a later Seedance video is a board,\nnot a single source frame; unless the user explicitly specifies a storyboard page/canvas/sheet\nshape, default the sheet image dimensions to a balanced grid that hosts the target\nscene-cell/frame aspect natively (portrait video target -> portrait or square sheet whose\ncolumns x rows grid produces ~9:16 cells; landscape video target -> landscape sheet whose\nrows x columns grid produces ~16:9 cells). Each scene-cell/frame area preserves the target\nvideo aspect ratio.\n\nSTORYBOARD IMAGE BATCH RULE: When rendering scene keyframes from a screenplay/storyboard,\nnumberOfVariations is only the count; the prompt MUST be one Dynamic Prompt branch with one\nfull keyframe prompt per scene:\n{scene 1 full keyframe prompt|scene 2 full keyframe prompt|...|scene N full keyframe prompt}.\nNEVER set numberOfVariations=N with only the first scene prompt — that creates N versions of\nscene 1. For full project requests, one generate_image batch for all scene keyframes, then\none animate_photo batch for all video clips in parallel.\n\nSTORYTELLING / BRAND / SOCIAL IMAGE PROMPTS: If generating a storyboard, ad concept,\ntrailer sheet, meme, creator post, or provocative social concept, make the first frame or\npanel immediately legible. Preserve the user's requested tone and audience. Use concrete\ncomposition, persona, product/brand role, caption placement, readable required text, and a\nclear visual transformation or punchline. For provocative adult social content, keep subjects\nclearly adult and consensual, PG-13/non-explicit, and avoid minor-coded styling or school-coded\nsettings while still optimizing visual magnet, persona, caption bait, and replay/comment value.\n\nGPT IMAGE 2 STORYBOARD SHEET → SEEDANCE AUTO-PROCEED: If the user asks to run the whole\nGPT Image 2 storyboard/keyframe sheet plus Seedance workflow without approval, the FIRST\ngenerate_image call must create ONE composite storyboard/keyframe sheet, not loose concept\nart and not separate keyframes. Use model=\"gpt-image-2\", numberOfVariations=1, and a\ncompiled storyboard prompt that literally includes: \"Create exactly N sequential video\nstoryboard frames as one composite storyboard image\", \"Target final video aspect ratio: X\",\na `SCENES:` section, and exactly N concrete scene entries named `SCENE_01`, `SCENE_02`,\netc. Each scene entry must include `Visual/Action:`, `Camera/Motion:`, `Dialogue/VO:`\n(use `[no dialogue]` when silent), `Audio/SFX:`, and any reference/visible-text notes\nneeded for that scene. Do not send only a source brief, storyboard concept, or generic\nlayout instructions as the prompt; malformed compiled storyboard prompts are blocked by\nquality audit instead of being repaired at runtime. Unless the user explicitly specifies another\nstoryboard page/canvas/sheet shape, default the GPT Image 2 storyboard sheet pixel dimensions\nto a balanced grid that hosts the target cell aspect natively: for a 9:16 portrait video,\npick a portrait-leaning sheet whose columns x rows grid produces ~9:16 cells (e.g., 12 cells\n-> ~3:4 sheet around 1728x2304, 6 cells -> ~27:32 around 1840x2176, 9 cells -> ~9:16 around\n1504x2672); for a 16:9 landscape video, pick a landscape sheet whose rows x columns grid\nproduces ~16:9 cells (e.g., 12 cells -> ~4:3 sheet around 2304x1728). Do not force landscape\n2560x1440 when cells are portrait — a landscape sheet with a portrait-cell grid cannot host\n9:16 cells without crushing them. Preserve the requested final video aspect ratio for every\nframe area. After\nthat image completes, call generate_video once using the generated storyboard board as\n@Image1/referenceImageIndices=[0], with skipPromptProcessing=false only when the user\nexplicitly wants the storyboard text rewritten; otherwise preserve the compiled shot guide\nand use skipPromptProcessing=true, expandPrompt=false.\n\nDO NOT USE generate_image FOR UPLOADED REFERENCE LOOPED VIDEO SEGMENTS: If the user says\nthe same uploaded image/reference should be reused as the first frame and last frame of each\nscripted segment/scene/clip before stitching, they are explicitly asking to animate the\nuploaded image, not to generate new storyboard keyframes. Do not call generate_image for\nthat request. Call animate_photo once with repeated uploaded source indices and per-scene\nprompts.\n\nREUSING RESULTS: When the user asks to redo, retry, or revise (e.g., \"try a new version\",\n\"redo the video with X\"), reuse the existing source images — do NOT regenerate them unless\nthe user explicitly asks for new images or describes changes to the images themselves.\nReference the existing result indices from the prior generation. If unsure whether the user\nwants new images, ask — don't regenerate by default.\n\nMODEL CHOICE: If the user asks for Krea 2 Turbo, choose model=\"krea-2-turbo\". If they ask for Dark Beast Krea 2, choose model=\"dark-beast-krea2\". If they ask for Dark Beast Z-Image Turbo, choose model=\"dark-beast-z-turbo\". If they ask for Chroma 1 HD, choose model=\"chroma1-hd\". If they ask for anime or anime-style output without naming a model, choose model=\"one-obsession-v22\". Base Z-image and Krea 2 Turbo image-to-image/enhancement requests stay on generate_image with sourceImageIndex and starting_image_strength; identity-preserving Krea edits with reference photos use edit_image instead.\n\nGPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality.",
+  "baseDescription": "generate_image creates images from text descriptions. Use for text-only image generation;\nuse edit_image when uploaded or reference images must guide identity/likeness.\nException: Z-image and Z-image Turbo image-to-image/enhancement requests use generate_image\nwith model=\"z-turbo\" or model=\"z-image\", sourceImageIndex=-1, and starting_image_strength;\ndo not route explicit Z-image Turbo uploaded-image enhancement to edit_image because\nedit_image does not expose Z-image models.\n\nIMAGE PROMPT ORDER: [SUBJECT] → [ATTRIBUTES] → [ACTION/POSE] → [CAMERA/FRAMING]\n→ [ENVIRONMENT] → [LIGHTING] → [STYLE/MEDIUM] → [MATERIALS/TEXTURES] →\n[SECONDARY DETAILS]. Always start with the main subject, never mood or atmosphere.\nUse concrete nouns and observable adjectives — \"soft overcast daylight\" not \"nice lighting\".\nGood defaults when user is underspecified: medium shot for portraits, wide shot for\nenvironments, eye-level angle, soft natural light for realism.\n\nDYNAMIC PROMPTS: When numberOfVariations > 1, use Dynamic Prompt syntax to make each\nvariation meaningfully different — not just seed-different. Syntax: {a|b|c} cycles\nsequentially, {@a|b|c} picks randomly, {~a|b} paired cycling across groups. Rules: (1) Vary\nONLY what the user left unspecified — lock in everything they specified. (2) Match option\ncount to numberOfVariations so every result is unique. (3) Briefly tell the user what you're\nvarying — never show raw {|} syntax. (4) Skip when: user wants consistency, prompt is fully\nspecified, user typed their own {|} syntax, or iterating on a specific result. (5) NEVER put\nthe count or the word \"versions\"/\"variations\" inside the prompt — the prompt always describes\na single image. The multiplicity comes ONLY from numberOfVariations + the {|} syntax.\nLINKED VARIANTS: when multiple attributes must stay paired per result, use ONE top-level\nDynamic Prompt branch with one complete self-contained prompt per output. Do NOT split\nlinked fields into separate Dynamic Prompt groups.\n\nSELECTION-GATED IMAGE STAGES: If the user asks for N image options and says they will pick\none before a later dance/video/animation, call generate_image once with numberOfVariations=N.\nAfter images are created, stop and ask the user to choose; do not call dance_montage,\nanimate_photo, or generate_video until they select.\n\nIMAGE→VIDEO DIMENSION RULE: When generating an image that will feed into a video tool\n(animate_photo, sound_to_video, etc.), the image MUST be generated at the SAME aspect\nratio and dimensions as the target video. Default video aspect ratio is 16:9 landscape —\npass aspectRatio=\"16:9\" (or the user's specified/reference ratio) so the source image\nmatches the video output. Never generate a square image for a widescreen video. Exception:\na composite GPT Image 2 storyboard/keyframe sheet for a later Seedance video is a board,\nnot a single source frame; unless the user explicitly specifies a storyboard page/canvas/sheet\nshape, default the sheet image dimensions to a balanced grid that hosts the target\nscene-cell/frame aspect natively (portrait video target -> portrait or square sheet whose\ncolumns x rows grid produces ~9:16 cells; landscape video target -> landscape sheet whose\nrows x columns grid produces ~16:9 cells). Each scene-cell/frame area preserves the target\nvideo aspect ratio.\n\nSTORYBOARD IMAGE BATCH RULE: When rendering scene keyframes from a screenplay/storyboard,\nnumberOfVariations is only the count; the prompt MUST be one Dynamic Prompt branch with one\nfull keyframe prompt per scene:\n{scene 1 full keyframe prompt|scene 2 full keyframe prompt|...|scene N full keyframe prompt}.\nNEVER set numberOfVariations=N with only the first scene prompt — that creates N versions of\nscene 1. For full project requests, one generate_image batch for all scene keyframes, then\none animate_photo batch for all video clips in parallel.\n\nSTORYTELLING / BRAND / SOCIAL IMAGE PROMPTS: If generating a storyboard, ad concept,\ntrailer sheet, meme, creator post, or provocative social concept, make the first frame or\npanel immediately legible. Preserve the user's requested tone and audience. Use concrete\ncomposition, persona, product/brand role, caption placement, readable required text, and a\nclear visual transformation or punchline. For provocative adult social content, keep subjects\nclearly adult and consensual, PG-13/non-explicit, and avoid minor-coded styling or school-coded\nsettings while still optimizing visual magnet, persona, caption bait, and replay/comment value.\n\nGPT IMAGE STORYBOARD SHEET → SEEDANCE AUTO-PROCEED: If the user asks to run the whole\nGPT Image storyboard/keyframe sheet plus Seedance workflow without approval, the FIRST\ngenerate_image call must create ONE composite storyboard/keyframe sheet, not loose concept\nart and not separate keyframes. Default to model=\"gpt-image-2.5-sunburst\" and preserve another\nexplicit GPT Image model named by the user. Use numberOfVariations=1 and a\ncompiled storyboard prompt that literally includes: \"Create exactly N sequential video\nstoryboard frames as one composite storyboard image\", \"Target final video aspect ratio: X\",\na `SCENES:` section, and exactly N concrete scene entries named `SCENE_01`, `SCENE_02`,\netc. Each scene entry must include `Visual/Action:`, `Camera/Motion:`, `Dialogue/VO:`\n(use `[no dialogue]` when silent), `Audio/SFX:`, and any reference/visible-text notes\nneeded for that scene. Do not send only a source brief, storyboard concept, or generic\nlayout instructions as the prompt; malformed compiled storyboard prompts are blocked by\nquality audit instead of being repaired at runtime. Unless the user explicitly specifies another\nstoryboard page/canvas/sheet shape, default the GPT Image 2 storyboard sheet pixel dimensions\nto a balanced grid that hosts the target cell aspect natively: for a 9:16 portrait video,\npick a portrait-leaning sheet whose columns x rows grid produces ~9:16 cells (e.g., 12 cells\n-> ~3:4 sheet around 1728x2304, 6 cells -> ~27:32 around 1840x2176, 9 cells -> ~9:16 around\n1504x2672); for a 16:9 landscape video, pick a landscape sheet whose rows x columns grid\nproduces ~16:9 cells (e.g., 12 cells -> ~4:3 sheet around 2304x1728). Do not force landscape\n2560x1440 when cells are portrait — a landscape sheet with a portrait-cell grid cannot host\n9:16 cells without crushing them. Preserve the requested final video aspect ratio for every\nframe area. After\nthat image completes, call generate_video once using the generated storyboard board as\n@Image1/referenceImageIndices=[0], with skipPromptProcessing=false only when the user\nexplicitly wants the storyboard text rewritten; otherwise preserve the compiled shot guide\nand use skipPromptProcessing=true, expandPrompt=false.\n\nDO NOT USE generate_image FOR UPLOADED REFERENCE LOOPED VIDEO SEGMENTS: If the user says\nthe same uploaded image/reference should be reused as the first frame and last frame of each\nscripted segment/scene/clip before stitching, they are explicitly asking to animate the\nuploaded image, not to generate new storyboard keyframes. Do not call generate_image for\nthat request. Call animate_photo once with repeated uploaded source indices and per-scene\nprompts.\n\nREUSING RESULTS: When the user asks to redo, retry, or revise (e.g., \"try a new version\",\n\"redo the video with X\"), reuse the existing source images — do NOT regenerate them unless\nthe user explicitly asks for new images or describes changes to the images themselves.\nReference the existing result indices from the prior generation. If unsure whether the user\nwants new images, ask — don't regenerate by default.\n\nMODEL CHOICE: If the user asks for Krea 2 Turbo, choose model=\"krea-2-turbo\". If they ask for Dark Beast Krea 2, choose model=\"dark-beast-krea2\". If they ask for Dark Beast Z-Image Turbo, choose model=\"dark-beast-z-turbo\". If they ask for Chroma 1 HD, choose model=\"chroma1-hd\". If they ask for anime or anime-style output without naming a model, choose model=\"one-obsession-v22\". Base Z-image and Krea 2 Turbo image-to-image/enhancement requests stay on generate_image with sourceImageIndex and starting_image_strength; identity-preserving Krea edits with reference photos use edit_image instead.\n\nGPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality.",
   "parameterDocs": {
     "prompt": "Text description. Follow image prompt order: subject first. Use Dynamic Prompt syntax when numberOfVariations > 1.",
     "numberOfVariations": "Number of distinct outputs. Use Dynamic Prompt {|} syntax to vary one attribute per image. Never put the count in the prompt itself.",

package/schemas/tools/animate_photo.schema.json

@@ -3,7 +3,7 @@
   "$id": "https://schemas.sogni.ai/creative-agent/2026-07-18.1/tools/animate_photo.schema.json",
   "title": "animate_photo arguments",
   "schemaVersion": "2026-07-18.1",
-  "description": "Animate a photo into video with motion, audio, and dialogue using LTX 2.5 by default, LTX 2.3 as rollback, or WAN 2.2. Do NOT use this tool for seedance2, seedance2-mini, or seedance2-5. Seedance media references — including Seedance 2.5 first-and-last-frame requests — must go through generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text in the prompt; for seamless-loop Seedance requests with one uploaded image, the prompt should anchor it as both the first frame and last frame. LTX/WAN NOTE: uploaded audio files are not loose references for ltx25/ltx23/wan22; use sound_to_video when uploaded audio is the primary sync target. DANCE REQUESTS (\"make them dance\", \"do the X dance\"): use dance_montage — NOT this tool. LTX 2.5 and LTX 2.3 generate audio natively — describe dialogue and ambient sounds directly in the prompt (do NOT pre-generate audio for this tool). If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Avoid placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. PERSONA PIPELINE: For persona videos, ensure an image of the persona exists before calling animate_photo. The standard pipeline is: resolve_personas → edit_image → animate_photo. If a suitable persona image already exists (user uploaded one, a prior edit_image/generate_image result, OR the user explicitly says to use the Persona image/reference photo directly), skip edit_image and animate directly. After resolve_personas, this tool can animate the injected persona image directly when that explicit direct-use instruction is given. Auto-uses the latest result image (from any prior tool) unless sourceImageIndex is set. Supports start-frame (default), end-frame, and start+end interpolation modes for LTX/WAN — ask the user which frame role their image should play if they mention \"end frame\", \"last frame\", or provide two images. FIRST+LAST FRAME WORKFLOW: When the user wants a non-Seedance video using two different scenes as start and end frames, prefer generating both images in a single generate_image/edit_image call with numberOfVariations=2 and Dynamic Prompts, then call animate_photo with frameRole=\"both\", sourceImageIndex=0, endImageIndex=1. If the user explicitly wants separately created frame assets, preserve that staged instruction while keeping indices correct. In frameRole=\"both\", the handler automatically inspects both images and upgrades the base prompt into a scene-aware smooth transition prompt, so your prompt should state the desired transition style, action, dialogue, and audio rather than trying to list every visible object. If the request is vague, analyze the image first and suggest 2-3 specific animation ideas tailored to what you see. Call once you have clear creative intent. N-VIDEOS PATTERN: Avoid sequential animate_photo calls for N outputs. For a single fixed source/end frame where only prompt text varies, use sourceImageIndex + numberOfVariations=N + one Dynamic Prompt branch in prompt so Sogni submits one project with multiple jobs. If the user explicitly asks for Dynamic Prompt or Dynamic Template syntax, prefer this one-project path whenever every output uses the same source/end frames and shared settings, even if they also ask to stitch the completed clips afterward. Use sourceImageIndices/prompts for multi-segment stitched non-Seedance video, different source/end assets, different audio windows, different durations/dimensions, isolated retry lifecycle, or other per-output parameters. sourceImageIndices supports up to 16 entries; there is NO 3-clip cap, so do not split one planned batch into \"first 3\" and \"remaining\" calls. For a dialogue-heavy total-duration request with no explicit per-clip duration, prefer 15-second clips on ltx25 by default (or ltx23 rollback) (30s total = 2 clips × 15s) and 10-second clips on wan22 (60s total on wan22 = 6 clips × 10s; do NOT pick 4 clips × 15s on wan22 — the wan22 worker rejects clips longer than 10s). Multi-source flavors: (A) SHARED CONTENT — when all N clips have the same dialogue/motion but different source visuals (different scenes, outfits, environments, persona looks), first generate N distinct images via ONE edit_image/generate_image call with numberOfVariations=N + Dynamic Prompts {|}, then call animate_photo with sourceImageIndices=[start..start+N-1] and a single shared `prompt`. If all segments intentionally reuse the primary uploaded image and only prompt text varies, use sourceImageIndex=-1, frameRole=\"both\" if requested, endImageIndex=-1 if requested, numberOfVariations=N, and one Dynamic Prompt branch in prompt. Each branch option must be a complete natural-language motion prompt; do not include \"clip N\", source-frame boilerplate, \"overall request context\", or instructions to follow the user request. For a long scripted/dialogue/storyboard video from a single supplied/uploaded image where each segment needs isolated exact dialogue or per-segment wiring, use sourceImageIndices=[-1,-1,...] and per-clip prompts. Only set frameRole=\"both\" and endImageIndex=-1 when the user explicitly says the same uploaded/source/original image should be both the first and last frame of every segment. If the user requests generated source images first, honor that image stage, then animate the generated result indices. When using generated scene keyframes and each clip should begin and end on its own scene image for stitching, call animate_photo with frameRole=\"both\" and sourceImageIndices=[start..end] but OMIT endImageIndex; do not set endImageIndex=-1 unless every source is the uploaded image. (B) PER-CLIP CONTENT — when source/end asset wiring or other per-output parameters differ, pass BOTH sourceImageIndices AND `prompts` (an array of N strings, one per clip) in the same single call. Each prompt must independently anchor the visible characters, scene action, camera, audio, exact screenplay-style speaker tags, and exact quoted dialogue for that segment. If you just wrote or displayed a script/table, copy the exact dialogue lines into the corresponding per-clip prompts; do not summarize them as speech activity. If using named speaker tags with any multi-person reference image or generated scene keyframe, include one explicit cast map in each prompt that binds each name to visible position, clothing, and props/actions, e.g. SPEAKER_A = left person holding a prop; SPEAKER_B = center person with tablet; SPEAKER_C = right person near table. Do not also describe the same people again as generic man/boy/girl/woman/character subjects. For screenplay, storyboard, commercial, series, or other longer-form tasks with recurring characters, preserve the same character names and repeated visual anchors in every per-clip prompt where each character appears. Use the standard single-source path (numberOfVariations only) when the user wants motion variety from a single fixed frame. Wan 3 first-frame and first+last-frame generation is supported with videoModel=\"wan3.0-video\". Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; it supports first-frame, last-frame-only, and first+last-frame generation, but frame anchors cannot be mixed with loose references.",
+  "description": "Animate a photo into video with motion, audio, and dialogue using LTX 2.5 by default, LTX 2.3 as rollback, or WAN 2.2. Do NOT use this tool for seedance2, seedance2-mini, seedance2-5, or seedance2-5-uncensored. Seedance media references — including Seedance 2.5 first-and-last-frame requests — must go through generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text in the prompt; for seamless-loop Seedance requests with one uploaded image, the prompt should anchor it as both the first frame and last frame. LTX/WAN NOTE: uploaded audio files are not loose references for ltx25/ltx23/wan22; use sound_to_video when uploaded audio is the primary sync target. DANCE REQUESTS (\"make them dance\", \"do the X dance\"): use dance_montage — NOT this tool. LTX 2.5 and LTX 2.3 generate audio natively — describe dialogue and ambient sounds directly in the prompt (do NOT pre-generate audio for this tool). If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Avoid placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. PERSONA PIPELINE: For persona videos, ensure an image of the persona exists before calling animate_photo. The standard pipeline is: resolve_personas → edit_image → animate_photo. If a suitable persona image already exists (user uploaded one, a prior edit_image/generate_image result, OR the user explicitly says to use the Persona image/reference photo directly), skip edit_image and animate directly. After resolve_personas, this tool can animate the injected persona image directly when that explicit direct-use instruction is given. Auto-uses the latest result image (from any prior tool) unless sourceImageIndex is set. Supports start-frame (default), end-frame, and start+end interpolation modes for LTX/WAN — ask the user which frame role their image should play if they mention \"end frame\", \"last frame\", or provide two images. FIRST+LAST FRAME WORKFLOW: When the user wants a non-Seedance video using two different scenes as start and end frames, prefer generating both images in a single generate_image/edit_image call with numberOfVariations=2 and Dynamic Prompts, then call animate_photo with frameRole=\"both\", sourceImageIndex=0, endImageIndex=1. If the user explicitly wants separately created frame assets, preserve that staged instruction while keeping indices correct. In frameRole=\"both\", the handler automatically inspects both images and upgrades the base prompt into a scene-aware smooth transition prompt, so your prompt should state the desired transition style, action, dialogue, and audio rather than trying to list every visible object. If the request is vague, analyze the image first and suggest 2-3 specific animation ideas tailored to what you see. Call once you have clear creative intent. N-VIDEOS PATTERN: Avoid sequential animate_photo calls for N outputs. For a single fixed source/end frame where only prompt text varies, use sourceImageIndex + numberOfVariations=N + one Dynamic Prompt branch in prompt so Sogni submits one project with multiple jobs. If the user explicitly asks for Dynamic Prompt or Dynamic Template syntax, prefer this one-project path whenever every output uses the same source/end frames and shared settings, even if they also ask to stitch the completed clips afterward. Use sourceImageIndices/prompts for multi-segment stitched non-Seedance video, different source/end assets, different audio windows, different durations/dimensions, isolated retry lifecycle, or other per-output parameters. sourceImageIndices supports up to 16 entries; there is NO 3-clip cap, so do not split one planned batch into \"first 3\" and \"remaining\" calls. For a dialogue-heavy total-duration request with no explicit per-clip duration, prefer 15-second clips on ltx25 by default (or ltx23 rollback) (30s total = 2 clips × 15s) and 10-second clips on wan22 (60s total on wan22 = 6 clips × 10s; do NOT pick 4 clips × 15s on wan22 — the wan22 worker rejects clips longer than 10s). Multi-source flavors: (A) SHARED CONTENT — when all N clips have the same dialogue/motion but different source visuals (different scenes, outfits, environments, persona looks), first generate N distinct images via ONE edit_image/generate_image call with numberOfVariations=N + Dynamic Prompts {|}, then call animate_photo with sourceImageIndices=[start..start+N-1] and a single shared `prompt`. If all segments intentionally reuse the primary uploaded image and only prompt text varies, use sourceImageIndex=-1, frameRole=\"both\" if requested, endImageIndex=-1 if requested, numberOfVariations=N, and one Dynamic Prompt branch in prompt. Each branch option must be a complete natural-language motion prompt; do not include \"clip N\", source-frame boilerplate, \"overall request context\", or instructions to follow the user request. For a long scripted/dialogue/storyboard video from a single supplied/uploaded image where each segment needs isolated exact dialogue or per-segment wiring, use sourceImageIndices=[-1,-1,...] and per-clip prompts. Only set frameRole=\"both\" and endImageIndex=-1 when the user explicitly says the same uploaded/source/original image should be both the first and last frame of every segment. If the user requests generated source images first, honor that image stage, then animate the generated result indices. When using generated scene keyframes and each clip should begin and end on its own scene image for stitching, call animate_photo with frameRole=\"both\" and sourceImageIndices=[start..end] but OMIT endImageIndex; do not set endImageIndex=-1 unless every source is the uploaded image. (B) PER-CLIP CONTENT — when source/end asset wiring or other per-output parameters differ, pass BOTH sourceImageIndices AND `prompts` (an array of N strings, one per clip) in the same single call. Each prompt must independently anchor the visible characters, scene action, camera, audio, exact screenplay-style speaker tags, and exact quoted dialogue for that segment. If you just wrote or displayed a script/table, copy the exact dialogue lines into the corresponding per-clip prompts; do not summarize them as speech activity. If using named speaker tags with any multi-person reference image or generated scene keyframe, include one explicit cast map in each prompt that binds each name to visible position, clothing, and props/actions, e.g. SPEAKER_A = left person holding a prop; SPEAKER_B = center person with tablet; SPEAKER_C = right person near table. Do not also describe the same people again as generic man/boy/girl/woman/character subjects. For screenplay, storyboard, commercial, series, or other longer-form tasks with recurring characters, preserve the same character names and repeated visual anchors in every per-clip prompt where each character appears. Use the standard single-source path (numberOfVariations only) when the user wants motion variety from a single fixed frame. Wan 3 first-frame and first+last-frame generation is supported with videoModel=\"wan3.0-video\". Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; it supports first-frame, last-frame-only, and first+last-frame generation, but frame anchors cannot be mixed with loose references.",
   "type": "object",
   "additionalProperties": false,
   "properties": {

package/schemas/tools/edit_image.schema.json

@@ -22,7 +22,7 @@
         "krea-identity-edit",
         "dark-beast-krea2-identity-edit"
       ],
-      "description": "The app auto-selects Fast→Qwen Lightning and HQ/Pro→full Qwen only for ordinary identity-neutral edits. REQUIRED IDENTITY DEFAULT: set \"krea-identity-edit\" whenever an edit of a referenced person or character must keep likeness or character identity while changing clothing, hair or makeup, pose or position, face/head/body, background, lighting, or visual style. Infer that semantic intent in any language; never route from keyword or regex matching. Also use it for a non-Pro single-character sheet. This default applies even when the user did not name Krea; an explicitly requested model always wins. Set \"dark-beast-krea2-identity-edit\" only when the user explicitly requests that model, its uncensored/community variant, or dark_beast_krea2_identity_edit_v1_2. Set \"gpt-image-2\" when the user explicitly names legacy GPT Image 2. Set \"gpt-image-2.5-sunburst\" when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets may use Sunburst. If GPT Image 2.5 Sunburst is unavailable for detail-critical layout work, fall back to full \"qwen\", never \"qwen-lightning\". Krea identity edit models require at least one reference image, accept up to two context images, and work best at 512-2048px. Let the model tier and worker choose current steps, guidance, sampler, scheduler, grounding, and reference-boost defaults; do not send a negative prompt. When Krea is selected, override the generic prompt-length guidance with a concise 1-4 sentence delta instruction; name only the requested change and details that must remain fixed. Put the base scene/image first and an optional person/detail reference second. Z-image, Z-image Turbo, and base Krea 2 Turbo are generate_image img2img models, not edit_image selectors. If the user names another edit/image model, honor it. GPT Image 2 always processes input images at high fidelity; do not set input_fidelity. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
+      "description": "The app auto-selects Fast→Qwen Lightning and HQ/Pro→full Qwen only for ordinary identity-neutral edits. REQUIRED IDENTITY DEFAULT: set \"krea-identity-edit\" whenever an edit of a referenced person or character must keep likeness or character identity while changing clothing, hair or makeup, pose or position, face/head/body, background, lighting, or visual style. Infer that semantic intent in any language; never route from keyword or regex matching. Also use it for a non-Pro single-character sheet. This default applies even when the user did not name Krea; an explicitly requested model always wins. Set \"dark-beast-krea2-identity-edit\" only when the user explicitly requests that model, its uncensored/community variant, or dark_beast_krea2_identity_edit_v1_2. Set \"gpt-image-2\" only when the user explicitly names legacy GPT Image 2 (GPT Image 2, GPT-2, or gpt-image-2); it is never a default. A ChatGPT, OpenAI, GPT, or GPT Image edit request that names no version uses \"gpt-image-2.5-flare\". Set \"gpt-image-2.5-sunburst\" when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets use Sunburst unless the user names another model. If GPT Image 2.5 Sunburst is unavailable for detail-critical layout work, fall back to full \"qwen\", never \"qwen-lightning\". Krea identity edit models require at least one reference image, accept up to two context images, and work best at 512-2048px. Let the model tier and worker choose current steps, guidance, sampler, scheduler, grounding, and reference-boost defaults; do not send a negative prompt. When Krea is selected, override the generic prompt-length guidance with a concise 1-4 sentence delta instruction; name only the requested change and details that must remain fixed. Put the base scene/image first and an optional person/detail reference second. Z-image, Z-image Turbo, and base Krea 2 Turbo are generate_image img2img models, not edit_image selectors. If the user names another edit/image model, honor it. GPT Image 2 always processes input images at high fidelity; do not set input_fidelity. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
     },
     "sourceImageIndex": {
       "type": "number",

package/schemas/tools/extend_video.schema.json

@@ -29,9 +29,10 @@
         "ltx23",
         "seedance2",
         "seedance2-mini",
-        "seedance2-5"
+        "seedance2-5",
+        "seedance2-5-uncensored"
       ],
-      "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance for a Seedance base and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. \"seedance2-5\" supports 480p/720p and 4-30s of new footage at 24 fps."
+      "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance for a Seedance base and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. \"seedance2-5\" and \"seedance2-5-uncensored\" (Seedance 2.5 Uncensored, only when requested) support 480p/720p and 4-30s of new footage at 24 fps."
     },
     "keepOriginalAudio": {
       "type": "boolean",

package/schemas/tools/generate_image.schema.json

@@ -42,7 +42,7 @@
         "pony-faetality",
         "dreamshaper-xl"
       ],
-      "description": "DO NOT SET THIS PARAMETER unless the user names a specific model, asks for a very complex image render, asks for a video storyboard/storyboard sheet/contact sheet/panel layout image, asks for anime without naming a model, requests permitted NSFW/nudity content, or explicitly asks for Z-image/Z-image Turbo/Krea 2 Turbo image-to-image. The app auto-selects based on quality settings. Set \"gpt-image-2\" when the user explicitly asks for legacy GPT Image 2. Set \"gpt-image-2.5-sunburst\" by default for complex single-image renders that need very strong text rendering, dense labels, crisp typography, multi-panel composition, timing notes, foley notes, professional storyboard-sheet layout, or a comprehensive character/mascot/model sheet with turnarounds, expressions, accessories, palette swatches, and brand notes. Set \"one-obsession-v22\" when the user asks for an anime or anime-style image and has not named a specific image model. Set \"z-turbo\" when the user asks for Z-image Turbo; set \"z-image\" when they ask for Z-image without Turbo. Set \"krea-2-turbo\" when the user asks for Krea 2 Turbo. If the user names another image model, honor that requested model instead. A model preference usually does not change which tool to use; the Z-image and Krea 2 Turbo image-to-image exception uses sourceImageIndex plus starting_image_strength on this tool. NSFW rule: \"gpt-image-2\"/Qwen image models CANNOT do nudity. For permitted NSFW/nudity content, prefer \"dark-beast-krea2\", then \"dark-beast-z-turbo\"; \"chroma1-hd\", \"pony-v7\", \"chroma-detail\", \"chroma-v46-flash\", and \"z-turbo\" are compatible fallbacks. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
+      "description": "DO NOT SET THIS PARAMETER unless the user names a specific model, asks for a very complex image render, asks for a video storyboard/storyboard sheet/contact sheet/panel layout image, asks for anime without naming a model, requests permitted NSFW/nudity content, or explicitly asks for Z-image/Z-image Turbo/Krea 2 Turbo image-to-image. The app auto-selects based on quality settings. Set \"gpt-image-2.5-flare\" when the user asks for a ChatGPT, OpenAI, GPT, or GPT Image image/model without naming a version. Set \"gpt-image-2\" only when the user explicitly names GPT Image 2, GPT-2, or gpt-image-2; GPT Image 2 is never a default. Set \"gpt-image-2.5-sunburst\" when the user explicitly requests very strong text rendering, and by default for video storyboards and other complex single-image renders that need dense labels, crisp typography, multi-panel composition, timing notes, foley notes, professional storyboard-sheet layout, or a comprehensive character/mascot/model sheet with turnarounds, expressions, accessories, palette swatches, and brand notes. Set \"one-obsession-v22\" when the user asks for an anime or anime-style image and has not named a specific image model. Set \"z-turbo\" when the user asks for Z-image Turbo; set \"z-image\" when they ask for Z-image without Turbo. Set \"krea-2-turbo\" when the user asks for Krea 2 Turbo. If the user names another image model, honor that requested model instead. A model preference usually does not change which tool to use; the Z-image and Krea 2 Turbo image-to-image exception uses sourceImageIndex plus starting_image_strength on this tool. NSFW rule: GPT Image models and Qwen image models CANNOT do nudity. For permitted NSFW/nudity content, prefer \"dark-beast-krea2\", then \"dark-beast-z-turbo\"; \"chroma1-hd\", \"pony-v7\", \"chroma-detail\", \"chroma-v46-flash\", and \"z-turbo\" are compatible fallbacks. GPT Image 2.5 adds two distinct models: use \"gpt-image-2.5-sunburst\" for an explicit Sunburst request and \"gpt-image-2.5-flare\" for an explicit Flare request. For GPT Image 2.5 without a named variant, use Flare. Preserve explicit GPT Image 2.0 as \"gpt-image-2\". Sunburst is positioned for difficult images and precise edits; Flare for faster everyday generation. Both generate and edit. Model choice is independent of rendering quality."
     },
     "width": {
       "type": "number",

package/schemas/tools/generate_video.schema.json

@@ -3,7 +3,7 @@
   "$id": "https://schemas.sogni.ai/creative-agent/2026-07-18.1/tools/generate_video.schema.json",
   "title": "generate_video arguments",
   "schemaVersion": "2026-07-18.1",
-  "description": "Generate a video from text or Seedance multimodal references. LTX 2.5 is the default and generates audio natively; LTX 2.3 remains available as rollback and also generates audio natively (dialogue, sounds, ambient music) — describe audio in the prompt. If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Never use placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. For non-Seedance syncing to a specific song or audio track, use sound_to_video instead. For non-Seedance animation from a locked source photo, use animate_photo. Do NOT use for My Personas unless generating a Seedance reference-based video — standard persona videos use resolve_personas → edit_image → animate_photo. SEEDANCE DEFAULT: For seedance2, seedance2-mini, or seedance2-5, default to exactly one video (4-15s on 2.0/Mini, 4-30s on seedance2-5) unless the user explicitly asks for multiple separate outputs. Multiple beats, shots, or scene descriptions in one up-to-15s Seedance prompt are still one video. If the user requests one continuous Seedance video longer than 15s, prefer seedance2-5, which renders up to 30s in a single call; beyond 30s (or on 2.0/Mini) preserve the requested total duration in the prompt/context and let chat orchestration split it into supported segment renders and stitch them instead of clamping it to a short excerpt. Uploaded/generated storyboard, shot-sheet, or trailer-concept images used as Seedance references should become one Seedance 2.5 generate_video call at targetResolution=1080 by default; preserve an explicitly requested model or resolution, and use Seedance 2.0 for 4K because Seedance 2.5 supports up to 1080p. Do not extract panels with edit_image and do not animate the storyboard sheet with LTX unless the user explicitly asks for separate non-Seedance clips. Seedance loose image, video, and audio references go through this tool; do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. If the uploaded audio is the primary sync target, lip-sync target, or requested as sound-to-video/audio-sync, use sound_to_video with videoModel=\"seedance2-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render and audit the composite board, generate one scene reference still per approved scene with GPT Image 2.5 Sunburst, render each scene as a Seedance 2.5 video segment at targetResolution=1080, then stitch the segments. Preserve an explicit alternate model or resolution. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent. WAN 3 uses the exact selector wan3.0-video: use this tool for text-to-video or loose Image 1/Video 1/Audio 1 references; use animate_photo for native first/last frames and sound_to_video when audio drives timing. A Wan 3 video reference conditions a new generation; it does not invoke a provider-backed edit or extend mode. Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; use this tool for prompt-only or loose-reference generation, and never combine loose references with frame anchors.",
+  "description": "Generate a video from text or Seedance multimodal references. LTX 2.5 is the default and generates audio natively; LTX 2.3 remains available as rollback and also generates audio natively (dialogue, sounds, ambient music) — describe audio in the prompt. If the user provides exact speech, include it in double quotes; if they only imply speech, describe the performance and voice without inventing quoted words. Never use placeholders such as \"while speaking\", \"dialogue begins\", \"explaining\", or \"final line lands\". PERSONA VOICE: Only when the user explicitly asks to use/clone a registered persona voice clip, call resolve_personas first, then set voicePersonaName to select which persona's voice clip to use. Do not set voicePersonaName for ordinary character dialogue or inferred voices; describe those voices in the prompt for native LTX audio. For cross-persona narration (e.g. David narrates a video of Aleyna), resolve both personas and set voicePersonaName to the narrator only if that registered voice was requested. Persona voice requires ltx23 because LTX 2.5 has no compatible ID-LoRA and WAN 2.2 does not support voice identity. For non-Seedance syncing to a specific song or audio track, use sound_to_video instead. For non-Seedance animation from a locked source photo, use animate_photo. Do NOT use for My Personas unless generating a Seedance reference-based video — standard persona videos use resolve_personas → edit_image → animate_photo. SEEDANCE DEFAULT: For seedance2, seedance2-mini, seedance2-5, or seedance2-5-uncensored, default to exactly one video (4-15s on 2.0/Mini, 4-30s on seedance2-5 and seedance2-5-uncensored) unless the user explicitly asks for multiple separate outputs. Multiple beats, shots, or scene descriptions in one up-to-15s Seedance prompt are still one video. If the user requests one continuous Seedance video longer than 15s, prefer seedance2-5, which renders up to 30s in a single call; beyond 30s (or on 2.0/Mini) preserve the requested total duration in the prompt/context and let chat orchestration split it into supported segment renders and stitch them instead of clamping it to a short excerpt. Uploaded/generated storyboard, shot-sheet, or trailer-concept images used as Seedance references should become one Seedance 2.5 generate_video call at targetResolution=1080 by default; preserve an explicitly requested model or resolution, and use Seedance 2.0 for 4K because Seedance 2.5 supports up to 1080p. Do not extract panels with edit_image and do not animate the storyboard sheet with LTX unless the user explicitly asks for separate non-Seedance clips. Seedance loose image, video, and audio references go through this tool; do not use animate_photo sourceImageIndex/frameRole/endImageIndex for Seedance. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. If the uploaded audio is the primary sync target, lip-sync target, or requested as sound-to-video/audio-sync, use sound_to_video with videoModel=\"seedance2-mini\" instead of this tool unless the user asks for full Seedance. Use referenceAudioIndices here only when audio is a loose reference under an image/video-anchored Seedance shot. For Seedance, every image — first frame, last frame, or loose reference — is passed through referenceImageIndices (auto-uploaded as referenceImageUrls). Anchor frame intent in the prompt with @Image tags such as \"Use @Image1 as the opening shot reference. Begin the video with a composition, subject placement, lighting, mood, and camera framing that closely match @Image1.\" (or @Image2 as the final shot reference). For seamless-loop or \"first frame and last frame identical\" requests with a single uploaded image, anchor it explicitly as both: \"Use @Image1 as both the first frame and last frame so the video loops cleanly back to the opening composition.\" Assign each useful @Image/@Video/@Audio tag a role. APPROVED STORYBOARD PRODUCTION: When the user asks for a production workflow from an approved storyboard, the chat orchestrator should use the durable CampaignStoryboard contract: render and audit the composite board, generate one scene reference still per approved scene with GPT Image 2.5 Sunburst, render each scene as a Seedance 2.5 video segment at targetResolution=1080, then stitch the segments. Preserve an explicit alternate model or resolution. Do not replace that with a generic storyboard-reference video unless the user asks for a fast draft. PARTIAL VIDEO EDITS: Do NOT call generate_video to re-render an existing rendered/uploaded video just to change part of it (the bumper, the intro, the end card, a single scene, the last few seconds, etc.). Use replace_video_segment for that — it preserves the unchanged portion, keeps the original audio outside the replaced window, and costs far less. Likewise use extend_video to add new time to the end without rewriting the rest. If the request is vague, ask about vision/mood/style first. Only call once you have clear creative intent. WAN 3 uses the exact selector wan3.0-video: use this tool for text-to-video or loose Image 1/Video 1/Audio 1 references; use animate_photo for native first/last frames and sound_to_video when audio drives timing. A Wan 3 video reference conditions a new generation; it does not invoke a provider-backed edit or extend mode. Wan 3.0 Enhanced uses Sogni selector wan3.0-spicy-video and MuleRouter provider ID w3.0-video; use this tool for prompt-only or loose-reference generation, and never combine loose references with frame anchors.",
   "type": "object",
   "additionalProperties": false,
   "properties": {
@@ -62,6 +62,7 @@
         "seedance2",
         "seedance2-mini",
         "seedance2-5",
+        "seedance2-5-uncensored",
         "minimax-h3-t2v",
         "minimax-h3-t2v-turbo",
         "minimax-h3-fasth3-t2v-turbo",
@@ -76,7 +77,7 @@
         "wan3.0-video",
         "wan3.0-spicy-video"
       ],
-      "description": "\"ltx25\" (default): LTX 2.5 with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Video model. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio. \"minimax-h3-t2v\": standard 20-step MiniMax H3 text-to-video; \"minimax-h3-t2v-turbo\": the existing 4-step LightX2V Turbo text-to-video; \"minimax-h3-fasth3-t2v-turbo\": the separate FastVideo VSA four-step FastH3 engine, about 2x faster and fixed to Euler/simple; \"minimax-h3-fasth3-t2v-turbo-2stage\": the two-stage FastH3 engine: FastH3 renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length and audio. targetResolution picks the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second, and 720 renders a 384px canvas (672x384 is delivered at 1344x768) for the regular FastH3 price of 4 Spark per second. The estimate prices every request. It takes the same inputs, durations and LoRAs as \"minimax-h3-fasth3-t2v-turbo\". Choose it when the user asks for 1080p, 1440p or 2K MiniMax H3 output, for two-stage output, or for the sharpest/best H3 quality; for ordinary 768p FastH3 output keep the regular FastH3 selector at targetResolution 768. All use native audio, fixed 24fps, 5.17-15.08s, and a 768p-class 32px-grid canvas; use animate_photo for H3 image-conditioned modes. Base and Turbo T2V/I2V/FLF2V prompts use the exact ordered fields integrated_multimodal_description, overall_soundscape, and non_diegetic_music; I2V/FLF2V prepend the official alignment line. \"minimax-h3-r2v\": standard 20-step MiniMax H3 reference-to-video; \"minimax-h3-r2v-turbo\": the dedicated LightX2V 4-step Ref2VA Turbo workflow using Euler/simple and a 960x544 default. \"minimax-h3-r2v-2stage\" (Standard, 20 steps, res_multistep/simple) and \"minimax-h3-r2v-balanced-2stage\" (Balanced, 8 steps, Euler/simple) are the two-stage reference-to-video forms: the tier renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length, audio and references. targetResolution names the delivered class exactly as for the FastH3 two-stage selectors: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088), 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536), and 720 renders a 384px canvas (672x384 is delivered at 1344x768). Each bills its tier's own per-second rate plus the two-stage surcharge of the delivered class (none at 720p); the estimate prices every request. Choose one when the user asks for 1080p, 1440p or 2K MiniMax H3 reference-to-video output; keep the one-stage \"minimax-h3-r2v\" or Balanced selector for ordinary 768p output. FastH3 has no R2V mode. Every R2V selector accepts up to 9 images, 3 videos, and 3 audios (12 files total); at least one visual reference (image or video) is required and audio alone is invalid. Select references with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and address them with the official <Subject N>/<Picture N>/<Video N>/<Audio N> semantics. Seedance quality is selected only by model: use \"seedance2-mini\" for Seedance 2.0 Mini or faster/lower-cost 720p iteration, use \"seedance2-5\" at targetResolution=1080 for generated/uploaded storyboard images and current high-quality Seedance generation unless the user explicitly requests another model or resolution, and use \"seedance2\" for Seedance 2.0 or 4K requests because Seedance 2.5 supports up to 1080p. Do not use Default Media Quality Fast/HQ/Pro to represent Seedance quality. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. Seedance supports multimodal loose reference assets. Seedance 2.0 and Mini accept up to 9 images, 3 videos, and 3 audios, with no more than 12 asset files total. Seedance 2.5 accepts up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Use @Image1/@Video1/@Audio1 style references in creative briefs when assigning roles. Assign every useful reference asset a role and prefer positive preservation constraints. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. Alibaba HappyHorse 1.1 video models (third-party vendor — requires Premium Spark). Select by mode: \"happyhorse-1.1-t2v\" for text-to-video, \"happyhorse-1.1-i2v\" for image-to-video from one first-frame image, and \"happyhorse-1.1-r2v\" for reference-to-video with up to 9 reference images. Resolutions 720P and 1080P; duration 3-15 seconds at 24 fps; native synchronized audio is always generated (do not set generateAudio or negativePrompt). Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9. HappyHorse 1.1 takes image references only and renders a native synchronized audio track (always on; do not set generateAudio or a negative prompt). Pick the model by mode: happyhorse-1.1-t2v for text-to-video (no reference image), happyhorse-1.1-i2v for image-to-video from a single first frame, and happyhorse-1.1-r2v for reference-to-video with 1 to 9 reference images. For r2v, tag the images in the prompt as [Image 1]…[Image 9] and assign each a clear role. HappyHorse does not accept reference videos or reference audios. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension."
+      "description": "\"ltx25\" (default): LTX 2.5 with native audio; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflow. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. Video model. \"ltx23\": LTX 2.3 rollback with native audio. \"wan22\": quick simple motion without audio. \"minimax-h3-t2v\": standard 20-step MiniMax H3 text-to-video; \"minimax-h3-t2v-turbo\": the existing 4-step LightX2V Turbo text-to-video; \"minimax-h3-fasth3-t2v-turbo\": the separate FastVideo VSA four-step FastH3 engine, about 2x faster and fixed to Euler/simple; \"minimax-h3-fasth3-t2v-turbo-2stage\": the two-stage FastH3 engine: FastH3 renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length and audio. targetResolution picks the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second, and 720 renders a 384px canvas (672x384 is delivered at 1344x768) for the regular FastH3 price of 4 Spark per second. The estimate prices every request. It takes the same inputs, durations and LoRAs as \"minimax-h3-fasth3-t2v-turbo\". Choose it when the user asks for 1080p, 1440p or 2K MiniMax H3 output, for two-stage output, or for the sharpest/best H3 quality; for ordinary 768p FastH3 output keep the regular FastH3 selector at targetResolution 768. All use native audio, fixed 24fps, 5.17-15.08s, and a 768p-class 32px-grid canvas; use animate_photo for H3 image-conditioned modes. Base and Turbo T2V/I2V/FLF2V prompts use the exact ordered fields integrated_multimodal_description, overall_soundscape, and non_diegetic_music; I2V/FLF2V prepend the official alignment line. \"minimax-h3-r2v\": standard 20-step MiniMax H3 reference-to-video; \"minimax-h3-r2v-turbo\": the dedicated LightX2V 4-step Ref2VA Turbo workflow using Euler/simple and a 960x544 default. \"minimax-h3-r2v-2stage\" (Standard, 20 steps, res_multistep/simple) and \"minimax-h3-r2v-balanced-2stage\" (Balanced, 8 steps, Euler/simple) are the two-stage reference-to-video forms: the tier renders the canvas, then the worker enlarges it 2x and refines it, so the clip is delivered at twice the canvas width and height with the same length, audio and references. targetResolution names the delivered class exactly as for the FastH3 two-stage selectors: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088), 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536), and 720 renders a 384px canvas (672x384 is delivered at 1344x768). Each bills its tier's own per-second rate plus the two-stage surcharge of the delivered class (none at 720p); the estimate prices every request. Choose one when the user asks for 1080p, 1440p or 2K MiniMax H3 reference-to-video output; keep the one-stage \"minimax-h3-r2v\" or Balanced selector for ordinary 768p output. FastH3 has no R2V mode. Every R2V selector accepts up to 9 images, 3 videos, and 3 audios (12 files total); at least one visual reference (image or video) is required and audio alone is invalid. Select references with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and address them with the official <Subject N>/<Picture N>/<Video N>/<Audio N> semantics. Seedance quality is selected only by model: use \"seedance2-mini\" for Seedance 2.0 Mini or faster/lower-cost 720p iteration, use \"seedance2-5\" at targetResolution=1080 for generated/uploaded storyboard images and current high-quality Seedance generation unless the user explicitly requests another model or resolution, and use \"seedance2\" for Seedance 2.0 or 4K requests because Seedance 2.5 supports up to 1080p. Do not use Default Media Quality Fast/HQ/Pro to represent Seedance quality. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. \"seedance2-5-uncensored\": Seedance 2.5 Uncensored — the uncensored variant of Seedance 2.5, with every mode, resolution, duration, reference limit, and output option described for \"seedance2-5\". Choose it only when the user asks for Seedance 2.5 Uncensored (including \"Seedance Uncensored\" or \"Seedance Spicy\") or for uncensored Seedance output; never swap it in for \"seedance2-5\" otherwise. Each account must accept a one-time likeness and consent agreement in the Sogni app before its first render; until then the job fails with error 4103, so tell the user to accept it in the Sogni app instead of retrying. Seedance supports multimodal loose reference assets. Seedance 2.0 and Mini accept up to 9 images, 3 videos, and 3 audios, with no more than 12 asset files total. Seedance 2.5 accepts up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Use @Image1/@Video1/@Audio1 style references in creative briefs when assigning roles. Assign every useful reference asset a role and prefer positive preservation constraints. If an uploaded video is the source clip to transform, upscale, enhance, restyle, or remaster, use video_to_video with controlMode=\"seedance-v2v\" instead of generate_video referenceVideoIndices. Alibaba HappyHorse 1.1 video models (third-party vendor — requires Premium Spark). Select by mode: \"happyhorse-1.1-t2v\" for text-to-video, \"happyhorse-1.1-i2v\" for image-to-video from one first-frame image, and \"happyhorse-1.1-r2v\" for reference-to-video with up to 9 reference images. Resolutions 720P and 1080P; duration 3-15 seconds at 24 fps; native synchronized audio is always generated (do not set generateAudio or negativePrompt). Supported aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9. HappyHorse 1.1 takes image references only and renders a native synchronized audio track (always on; do not set generateAudio or a negative prompt). Pick the model by mode: happyhorse-1.1-t2v for text-to-video (no reference image), happyhorse-1.1-i2v for image-to-video from a single first frame, and happyhorse-1.1-r2v for reference-to-video with 1 to 9 reference images. For r2v, tag the images in the prompt as [Image 1]…[Image 9] and assign each a clear role. HappyHorse does not accept reference videos or reference audios. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension."
     },
     "generateAudio": {
       "type": "boolean",
@@ -113,7 +114,7 @@
     },
     "targetResolution": {
       "type": "number",
-      "description": "Short-side video resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact pixels or an output orientation. This is resolution only, not a Seedance quality tier: Seedance quality is selected by videoModel (\"seedance2\" vs \"seedance2-mini\" vs \"seedance2-5\"). Seedance 2.0 full supports 4K; Seedance Mini supports 480p/720p; Seedance 2.5 supports 480p/720p/1080p, so never set 4K for \"seedance2-5\". Wan 3 supports exactly 480p, 720p, and 1080p. HappyHorse supports only 720p and 1080p. Never set 4K for Wan 3 or HappyHorse. MiniMax H3 renders inside a 1344x768 pixel budget on a 32px grid, so use 768 for the regular H3 selectors and never 1080p or 4K. The two-stage H3 selector \"minimax-h3-fasth3-t2v-turbo-2stage\" delivers twice the canvas, so there targetResolution names the delivered short-edge class: 1080 (544px canvas short edge: 960x544 delivered at 1920x1088), 1440 for 2K (the 1344x768 canvas delivered at 2688x1536), or 720 (384px canvas: 672x384 delivered at 1344x768); omit it for 2K. Never set 4K for H3. Do not set targetResolution from Default Media Quality Fast/HQ/Pro. If omitted for Seedance, Wan 3, HappyHorse, or MiniMax H3, the host uses the selected model default. This preserves/inherits the current video shape instead of forcing landscape. Do NOT set width, height, or exact-pixel aspectRatio for bare named resolution requests. If the user says \"720p portrait\", \"720p landscape\", \"4K portrait\", or \"4K landscape\", use exact width/height/aspectRatio instead."
+      "description": "Short-side video resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact pixels or an output orientation. This is resolution only, not a Seedance quality tier: Seedance quality is selected by videoModel (\"seedance2\" vs \"seedance2-mini\" vs \"seedance2-5\"). Seedance 2.0 full supports 4K; Seedance Mini supports 480p/720p; Seedance 2.5 supports 480p/720p/1080p, so never set 4K for \"seedance2-5\" or \"seedance2-5-uncensored\". Wan 3 supports exactly 480p, 720p, and 1080p. HappyHorse supports only 720p and 1080p. Never set 4K for Wan 3 or HappyHorse. MiniMax H3 renders inside a 1344x768 pixel budget on a 32px grid, so use 768 for the regular H3 selectors and never 1080p or 4K. The two-stage H3 selector \"minimax-h3-fasth3-t2v-turbo-2stage\" delivers twice the canvas, so there targetResolution names the delivered short-edge class: 1080 (544px canvas short edge: 960x544 delivered at 1920x1088), 1440 for 2K (the 1344x768 canvas delivered at 2688x1536), or 720 (384px canvas: 672x384 delivered at 1344x768); omit it for 2K. Never set 4K for H3. Do not set targetResolution from Default Media Quality Fast/HQ/Pro. If omitted for Seedance, Wan 3, HappyHorse, or MiniMax H3, the host uses the selected model default. This preserves/inherits the current video shape instead of forcing landscape. Do NOT set width, height, or exact-pixel aspectRatio for bare named resolution requests. If the user says \"720p portrait\", \"720p landscape\", \"4K portrait\", or \"4K landscape\", use exact width/height/aspectRatio instead."
     },
     "numberOfVariations": {
       "type": "number",

package/schemas/tools/replace_video_segment.schema.json

@@ -46,9 +46,10 @@
         "wan22",
         "seedance2",
         "seedance2-mini",
-        "seedance2-5"
+        "seedance2-5",
+        "seedance2-5-uncensored"
       ],
-      "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance or WAN for matching base clips and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. \"seedance2-5\" supports 480p/720p and 4-30s replacement windows at 24 fps."
+      "description": "Which model to use for the new segment. Default: \"auto\" — preserve Seedance or WAN for matching base clips and otherwise use LTX 2.5. Use ltx23 only for explicit rollback. \"seedance2-5\" and \"seedance2-5-uncensored\" (Seedance 2.5 Uncensored, only when requested) support 480p/720p and 4-30s replacement windows at 24 fps."
     },
     "keepOriginalAudio": {
       "type": "boolean",

package/schemas/tools/sound_to_video.schema.json

@@ -3,7 +3,7 @@
   "$id": "https://schemas.sogni.ai/creative-agent/2026-07-18.1/tools/sound_to_video.schema.json",
   "title": "sound_to_video arguments",
   "schemaVersion": "2026-07-18.1",
-  "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx25-ia2v by default (ltx23-ia2v is rollback); for lip-sync with a face image, use wan-s2v; if no image, use ltx25-a2v by default (ltx23-a2v is rollback). If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.5 and LTX 2.3 generate audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video with videoModel=\"ltx23\" because LTX 2.5 has no compatible ID-LoRA. LONG AUDIO ON SEEDANCE: Seedance 2.0 and Mini cap each clip at 15s; Seedance 2.5 renders up to 30s in one call, so prefer seedance2-5 for 16-30s audio instead of splitting. When the user uploads audio longer than the per-clip cap of the selected model and Seedance is selected (seedance2, seedance2-mini, or seedance2-5), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them. Use videoModel=\"wan3.0-video\" when the user explicitly requests Wan 3 audio-driven video. Use videoModel=\"wan3.0-spicy-video\" for Wan 3.0 Enhanced audio-driven video through MuleRouter provider ID w3.0-video; it supports adaptive ratios and provider prompt expansion. MINIMAX H3 AUDIO: only when the user asks for MiniMax H3 or FastH3 audio-driven video, use videoModel=\"minimax-h3-fasth3-ia2v-turbo\" with a first-frame image (sourceImageIndex), \"minimax-h3-fasth3-flfa2v-turbo\" with a first and a last frame (sourceImageIndex and endImageIndex), or \"minimax-h3-fasth3-a2v-turbo\" with no image; add \"-2stage\" only for 1080p, 1440p or 2K H3 output. Without an explicit MiniMax H3 or FastH3 request keep the LTX 2.5 defaults. The MiniMax H3 selectors on generate_video and animate_photo cannot take an uploaded audio track; send uploaded-audio H3 requests here.",
+  "description": "Generate video synchronized to audio. Use when the user has uploaded an audio file (mp3, wav, m4a, flac) and the audio is the primary sync target, especially uploaded-audio-only workflows. Also use after generate_music (\"turn that song into a video\", \"make a music video from that\"). Auto-detects generated audio from generate_music if no audio file is uploaded. Seedance animate_photo/generate_video can also attach uploaded audio as a loose @Audio reference when an image or video reference anchors the request; use this tool instead when the soundtrack itself should drive the video. If the user provides a reference image, use ltx25-ia2v by default (ltx23-ia2v is rollback); for lip-sync with a face image, use wan-s2v; if no image, use ltx25-a2v by default (ltx23-a2v is rollback). If the user wants dialogue/audio WITHOUT pre-existing audio, use animate_photo instead (LTX 2.5 and LTX 2.3 generate audio natively). Note: Persona voice clips from resolve_personas are NOT used by this tool — for persona voice identity in video, use animate_photo or generate_video with videoModel=\"ltx23\" because LTX 2.5 has no compatible ID-LoRA. LONG AUDIO ON SEEDANCE: Seedance 2.0 and Mini cap each clip at 15s; Seedance 2.5 renders up to 30s in one call, so prefer seedance2-5 for 16-30s audio instead of splitting. When the user uploads audio longer than the per-clip cap of the selected model and Seedance is selected (seedance2, seedance2-mini, seedance2-5, or seedance2-5-uncensored), do NOT clamp to 15s and drop the rest — split the run into multiple sound_to_video calls in the same turn (one per 15s segment, so a 20s audio becomes two clips: audioStart=0 duration=15, then audioStart=15 duration=5) and finish with a single stitch_video call referencing the resulting clip indices in order with audioIndex pointing at the same uploaded audio so the stitched output carries the full original soundtrack. LTX/WAN models accept up to 20s per clip, so single-call is fine for them. Use videoModel=\"wan3.0-video\" when the user explicitly requests Wan 3 audio-driven video. Use videoModel=\"wan3.0-spicy-video\" for Wan 3.0 Enhanced audio-driven video through MuleRouter provider ID w3.0-video; it supports adaptive ratios and provider prompt expansion. MINIMAX H3 AUDIO: only when the user asks for MiniMax H3 or FastH3 audio-driven video, use videoModel=\"minimax-h3-fasth3-ia2v-turbo\" with a first-frame image (sourceImageIndex), \"minimax-h3-fasth3-flfa2v-turbo\" with a first and a last frame (sourceImageIndex and endImageIndex), or \"minimax-h3-fasth3-a2v-turbo\" with no image; add \"-2stage\" only for 1080p, 1440p or 2K H3 output. Without an explicit MiniMax H3 or FastH3 request keep the LTX 2.5 defaults. The MiniMax H3 selectors on generate_video and animate_photo cannot take an uploaded audio track; send uploaded-audio H3 requests here.",
   "type": "object",
   "additionalProperties": false,
   "properties": {
@@ -73,6 +73,7 @@
         "seedance2",
         "seedance2-mini",
         "seedance2-5",
+        "seedance2-5-uncensored",
         "ltx25-ia2v",
         "ltx25-a2v",
         "ltx23-ia2v",
@@ -86,7 +87,7 @@
         "minimax-h3-fasth3-a2v-turbo",
         "minimax-h3-fasth3-a2v-turbo-2stage"
       ],
-      "description": "\"ltx25-ia2v\" (default with image) and \"ltx25-a2v\" (default without image): LTX 2.5 image+audio and audio-only modes; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflows. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates official ComfyUI Dev recipes. Video model. \"ltx23-ia2v\" (rollback with image): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. \"ltx23-a2v\" (rollback without image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s. \"seedance2-mini\": Seedance 2.0 Mini, 720p cap, fastest/lower-cost Seedance option. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster/lower-cost drafts or explicit Mini requests, and pick \"seedance2\" for full-quality Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension. MiniMax H3 FastH3 audio guide: \"minimax-h3-fasth3-ia2v-turbo\" (first-frame image from sourceImageIndex plus the audio), \"minimax-h3-fasth3-flfa2v-turbo\" (first frame from sourceImageIndex, last frame from endImageIndex, plus the audio) and \"minimax-h3-fasth3-a2v-turbo\" (audio only; set neither sourceImageIndex nor endImageIndex) run the four-step FastH3 engine with the uploaded audio driving the picture from frame 0, and the output keeps that audio as its soundtrack. Choose them only when the user asks for MiniMax H3 or FastH3; never pick them in place of the LTX 2.5 defaults. They render 124-362 frames on the H3 17-frame grid at a fixed 24 fps (about 5.2-15.1 seconds) on a 32px grid within 1344x768, so use targetResolution 768 or omit it. audioStart picks the window of the upload. MiniMax H3 catalog and Personal LoRAs are supported across audio modes and tiers. generateAudio=false and negativePrompt are not supported. Each costs the FastH3 price of its image-to-video, first-and-last-frame or text-to-video mode, 4 Spark per second. \"minimax-h3-fasth3-ia2v-turbo-2stage\", \"minimax-h3-fasth3-flfa2v-turbo-2stage\" and \"minimax-h3-fasth3-a2v-turbo-2stage\" are the two-stage forms: the same inputs rendered on the FastH3 canvas, then enlarged 2x and refined, delivered at twice the canvas with the same length and audio. For them targetResolution names the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, and 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second. The audio two-stage selectors have no 720p price class (720 would render a 384px canvas at the 1080p rate), so for 720p or 768p audio-guided H3 output use the regular selector. The estimate prices every request."
+      "description": "\"ltx25-ia2v\" (default with image) and \"ltx25-a2v\" (default without image): LTX 2.5 image+audio and audio-only modes; Fast, HQ, and Pro currently use the release-validated official Distilled INT8 workflows. The Dev checkpoints are not publicly routed until upstream publishes and Sogni validates official ComfyUI Dev recipes. Video model. \"ltx23-ia2v\" (rollback with image): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step worker and Default Media Quality Pro uses the non-distilled dev worker. \"ltx23-a2v\" (rollback without image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s. \"seedance2-mini\": Seedance 2.0 Mini, 720p cap, fastest/lower-cost Seedance option. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster/lower-cost drafts or explicit Mini requests, and pick \"seedance2\" for full-quality Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p, 720p, and 1080p (4K is unsupported), 4-30s per clip at a fixed 24 fps, native audio, first-and-last-frame conditioning, and a much larger reference budget than the 2.0 family: up to 30 images, 10 videos, and 10 audios, with up to 50 reference media files total, subject to those per-modality caps. Choose \"seedance2-5\" when the user asks for Seedance 2.5, wants a single continuous Seedance clip longer than 15s (2.5 renders up to 30s in one call instead of being split and stitched), or wants a first-and-last-frame Seedance transition. Keep \"seedance2\" for 4K requests; Seedance 2.5 supports up to 1080p. \"seedance2-5-uncensored\": Seedance 2.5 Uncensored — the uncensored variant of Seedance 2.5, with every mode, resolution, duration, reference limit, and output option described for \"seedance2-5\". Choose it only when the user asks for Seedance 2.5 Uncensored (including \"Seedance Uncensored\" or \"Seedance Spicy\") or for uncensored Seedance output; never swap it in for \"seedance2-5\" otherwise. Each account must accept a one-time likeness and consent agreement in the Sogni app before its first render; until then the job fails with error 4103, so tell the user to accept it in the Sogni app instead of retrying. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present. \"wan3.0-video\" is Alibaba Wan 3 and \"wan3.0-spicy-video\" is MuleRouter w3.0-video. Both render 2-30s at fixed 30 fps with optional native audio, provider prompt expansion, 480p/720p/1080p, adaptive/fixed ratios, first/last frames, and up to 10 image/5 video/5 audio references. Only Alibaba wan3.0-video accepts document/web context and watermark. Frame anchors and loose references are mutually exclusive. Do not send negativePrompt; video references are loose conditioning for a new result, not source-video editing or extension. MiniMax H3 FastH3 audio guide: \"minimax-h3-fasth3-ia2v-turbo\" (first-frame image from sourceImageIndex plus the audio), \"minimax-h3-fasth3-flfa2v-turbo\" (first frame from sourceImageIndex, last frame from endImageIndex, plus the audio) and \"minimax-h3-fasth3-a2v-turbo\" (audio only; set neither sourceImageIndex nor endImageIndex) run the four-step FastH3 engine with the uploaded audio driving the picture from frame 0, and the output keeps that audio as its soundtrack. Choose them only when the user asks for MiniMax H3 or FastH3; never pick them in place of the LTX 2.5 defaults. They render 124-362 frames on the H3 17-frame grid at a fixed 24 fps (about 5.2-15.1 seconds) on a 32px grid within 1344x768, so use targetResolution 768 or omit it. audioStart picks the window of the upload. MiniMax H3 catalog and Personal LoRAs are supported across audio modes and tiers. generateAudio=false and negativePrompt are not supported. Each costs the FastH3 price of its image-to-video, first-and-last-frame or text-to-video mode, 4 Spark per second. \"minimax-h3-fasth3-ia2v-turbo-2stage\", \"minimax-h3-fasth3-flfa2v-turbo-2stage\" and \"minimax-h3-fasth3-a2v-turbo-2stage\" are the two-stage forms: the same inputs rendered on the FastH3 canvas, then enlarged 2x and refined, delivered at twice the canvas with the same length and audio. For them targetResolution names the delivered class: 1080 renders a 544px short-edge canvas (960x544 is delivered at 1920x1088) for 10 Spark per second, and 1440 or omitted renders the 768p canvas for 2K (1344x768 is delivered at 2688x1536) for 16 Spark per second. The audio two-stage selectors have no 720p price class (720 would render a 384px canvas at the 1080p rate), so for 720p or 768p audio-guided H3 output use the regular selector. The estimate prices every request."
     },
     "generateAudio": {
       "type": "boolean",

package/schemas/tools/video_to_video.schema.json

@@ -36,7 +36,7 @@
     },
     "negativePrompt": {
       "type": "string",
-      "description": "Advanced non-Seedance only. Use this field only when the user explicitly asks to set a separate negative prompt. For ordinary avoid/no/don't constraints on LTX 2.3 or WAN 2.2, translate them into affirmative production constraints inside prompt instead; do not move them here. Do not set when controlMode is seedance-v2v or videoModel is seedance2/seedance2-mini/seedance2-5."
+      "description": "Advanced non-Seedance only. Use this field only when the user explicitly asks to set a separate negative prompt. For ordinary avoid/no/don't constraints on LTX 2.3 or WAN 2.2, translate them into affirmative production constraints inside prompt instead; do not move them here. Do not set when controlMode is seedance-v2v or videoModel is seedance2/seedance2-mini/seedance2-5/seedance2-5-uncensored."
     },
     "videoModel": {
       "type": "string",
@@ -46,9 +46,10 @@
         "wan22-animate",
         "seedance2",
         "seedance2-mini",
-        "seedance2-5"
+        "seedance2-5",
+        "seedance2-5-uncensored"
       ],
-      "description": "Model selector for this video-to-video request. Usually omit: non-Seedance controls default to \"ltx25-v2v\"; use \"ltx23-v2v\" only for rollback. LTX 2.5 Fast, HQ, and Pro currently use the release-validated official Distilled workflow for canny, pose, depth, detailer, inpaint, and outpaint. Dev is not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. For controlMode=\"seedance-v2v\", Seedance quality is selected only by model: use \"seedance2-mini\" for faster/lower-cost drafts and use \"seedance2\" for full-quality Seedance or 1080p/4K. \"seedance2-5\" supports 480p/720p/1080p, 4-30s at 24 fps, native audio, and first/last-frame conditioning; keep \"seedance2\" for 4K."
+      "description": "Model selector for this video-to-video request. Usually omit: non-Seedance controls default to \"ltx25-v2v\"; use \"ltx23-v2v\" only for rollback. LTX 2.5 Fast, HQ, and Pro currently use the release-validated official Distilled workflow for canny, pose, depth, detailer, inpaint, and outpaint. Dev is not publicly routed until upstream publishes and Sogni validates an official ComfyUI Dev recipe. For controlMode=\"seedance-v2v\", Seedance quality is selected only by model: use \"seedance2-mini\" for faster/lower-cost drafts and use \"seedance2\" for full-quality Seedance or 1080p/4K. \"seedance2-5\" supports 480p/720p/1080p, 4-30s at 24 fps, native audio, and first/last-frame conditioning; keep \"seedance2\" for 4K. \"seedance2-5-uncensored\": Seedance 2.5 Uncensored — the uncensored variant of Seedance 2.5, with every mode, resolution, duration, reference limit, and output option described for \"seedance2-5\". Choose it only when the user asks for Seedance 2.5 Uncensored (including \"Seedance Uncensored\" or \"Seedance Spicy\") or for uncensored Seedance output; never swap it in for \"seedance2-5\" otherwise. Each account must accept a one-time likeness and consent agreement in the Sogni app before its first render; until then the job fails with error 4103, so tell the user to accept it in the Sogni app instead of retrying."
     },
     "generateAudio": {
       "type": "boolean",
@@ -56,7 +57,7 @@
     },
     "targetResolution": {
       "type": "number",
-      "description": "Seedance V2V only. Short-side output resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact dimensions. Seedance V2V full supports 4K; Seedance V2V Mini and Fast support 480p and 720p only; Seedance 2.5 also supports 1080p, so never set 4K for \"seedance2-5\". Preserve the source video shape instead of forcing landscape pixels."
+      "description": "Seedance V2V only. Short-side output resolution target in pixels. Use when the user asks for a bare named resolution such as \"480p\", \"720p\", \"1080p\", \"2160p\", or \"4K\" without exact dimensions. Seedance V2V full supports 4K; Seedance V2V Mini and Fast support 480p and 720p only; Seedance 2.5 also supports 1080p, so never set 4K for \"seedance2-5\" or \"seedance2-5-uncensored\". Preserve the source video shape instead of forcing landscape pixels."
     },
     "sourceImageIndex": {
       "type": "number",

package/version.json

@@ -1,4 +1,4 @@
 {
-  "protocolVersion": "7.6.0",
+  "protocolVersion": "7.7.0",
   "description": "Sogni protocol artifact version. SDKs may refuse to operate against a protocolVersion they were not built for. Bump the major when removing or renaming any schema / enum / manifest field; bump the minor when adding new optional fields or new tools; bump the patch for description / prose changes only."
 }