@sogni-ai/sogni-protocol 1.0.0-alpha.19 → 1.0.0-alpha.20

package/README.md

@@ -24,7 +24,7 @@ This package ships pure data — JSON Schemas, OpenAI tool manifests, prompt con
 | `enums/chat-run-waiting-reasons.json` | Why a run is paused for user input. | All SDKs. |
 | `enums/token-types.json` | Sogni billing token types (`sogni`, `spark`). | All SDKs. |
 | `catalogs/quality-presets.json` | Quality tier presets (fast/hq/pro) -> model + sampling parameters. | UI SDKs rendering quality toggles. |
-| `catalogs/audio-models.json` | ACE-Step audio model capability table + duration/BPM/time-signature constraints. | SDKs validating music-gen input. |
+| `catalogs/audio-models.json` | ACE-Step + MiniMax Music 3 audio model capability table + duration/BPM/time-signature constraints. | SDKs validating music-gen input. |
 | `version.json` | Protocol version for compatibility checks. | All SDKs. |
 
 ## Why a separate package

package/catalogs/audio-models.json

@@ -1,20 +1,76 @@
 {
-  "description": "Audio / music generation model catalog. ACE-Step 1.5 family. Each entry lists per-parameter ranges so SDKs can validate user input and render sliders without round-tripping to the server. Cross-cutting audio constraints (duration, BPM, time signatures) live in the top-level `constraints` block.",
+  "description": "Audio / music generation model catalog. ACE-Step 1.5 family plus MiniMax Music 3. Each entry lists per-parameter ranges so SDKs can validate user input and render sliders without round-tripping to the server. Cross-cutting audio constraints (duration, BPM, time signatures) live in the top-level `constraints` block; models with different limits carry a per-model `constraints` override.",
   "default": "turbo",
   "models": {
     "turbo": {
       "id": "ace_step_1.5_turbo",
       "name": "ACE-Step 1.5 Turbo",
-      "steps": { "min": 4, "max": 16, "default": 8 },
-      "shift": { "min": 1, "max": 5, "default": 3 },
+      "steps": {
+        "min": 4,
+        "max": 16,
+        "default": 8
+      },
+      "shift": {
+        "min": 1,
+        "max": 5,
+        "default": 3
+      },
       "guidance": null
     },
     "sft": {
       "id": "ace_step_1.5_sft",
       "name": "ACE-Step 1.5 SFT",
-      "steps": { "min": 10, "max": 200, "default": 50 },
-      "shift": { "min": 1, "max": 5, "default": 3 },
-      "guidance": { "min": 1, "max": 15, "default": 5 }
+      "steps": {
+        "min": 10,
+        "max": 200,
+        "default": 50
+      },
+      "shift": {
+        "min": 1,
+        "max": 5,
+        "default": 3
+      },
+      "guidance": {
+        "min": 1,
+        "max": 15,
+        "default": 5
+      }
+    },
+    "music3": {
+      "id": "minimax_music3",
+      "name": "MiniMax Music 3",
+      "steps": {
+        "min": 10,
+        "max": 100,
+        "default": 30
+      },
+      "shift": null,
+      "guidance": {
+        "min": 1,
+        "max": 5,
+        "default": 1.7
+      },
+      "promptStrength": {
+        "min": 0,
+        "max": 10,
+        "default": 1.7
+      },
+      "topK": {
+        "min": 1,
+        "max": 16384,
+        "default": 50
+      },
+      "constraints": {
+        "duration": {
+          "min": 10,
+          "max": 300,
+          "default": 60,
+          "unit": "seconds",
+          "note": "Maximum duration; the planner composes an ending and may stop earlier."
+        },
+        "bpm": null,
+        "timeSignatures": null
+      }
     }
   },
   "constraints": {
@@ -29,6 +85,11 @@
       "max": 300,
       "default": 120
     },
-    "timeSignatures": [2, 3, 4, 6]
+    "timeSignatures": [
+      2,
+      3,
+      4,
+      6
+    ]
   }
 }

package/catalogs/quality-presets.json

@@ -19,12 +19,12 @@
       "description": "More detail"
     },
     "pro": {
-      "model": "flux2_dev_fp8",
-      "steps": 40,
+      "model": "qwen_image_edit_2511_fp8",
+      "steps": 25,
       "guidance": 4.0,
       "outputFormat": "jpg",
       "label": "Pro",
-      "description": "Flux.2 Dev"
+      "description": "Maximum Qwen detail"
     }
   }
 }

package/manifests/composition-tools.json

@@ -20,7 +20,7 @@
           "properties": {
             "prompt": { "type": "string", "description": "The source prompt, rough idea, or prompt revision request to enhance." },
             "target_output": { "type": "string", "enum": ["image_prompt", "video_prompt", "music_prompt", "edit_prompt", "model_prompt", "general_prompt"], "description": "The kind of prompt artifact to produce." },
-            "destination_model": { "type": "string", "description": "Optional destination model selector, such as seedance2, ltx23, wan22, flux2, gpt-image-2, or sdxl." },
+            "destination_model": { "type": "string", "description": "Optional destination model selector, such as seedance2, ltx23, wan22, gpt-image-2, or sdxl." },
             "destination_tool": { "type": "string", "description": "Optional downstream generation tool, such as generate_image, edit_image, generate_video, animate_photo, sound_to_video, video_to_video, or generate_music." },
             "prompting_type": { "type": "string", "enum": ["flux", "sdxl", "sd15", "pony", "fast", "sd3", "editing", "video"], "description": "Optional image-prompting family when producing an image prompt." },
             "model_title": { "type": "string", "description": "Optional human-readable target model name for image prompt guidance." },
@@ -131,7 +131,7 @@
               "type": "object",
               "additionalProperties": false,
               "properties": {
-                "image": { "type": "string", "description": "Preferred image model (e.g., 'flux2', 'gpt-image-2')." },
+                "image": { "type": "string", "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')." },
                 "video": { "type": "string", "description": "Preferred video model (e.g., 'ltx23', 'wan22', 'seedance2')." },
                 "music": { "type": "string", "description": "Preferred music model." }
               }
@@ -207,7 +207,7 @@
               "type": "object",
               "additionalProperties": false,
               "properties": {
-                "image": { "type": "string", "description": "Preferred image model (e.g., 'flux2', 'gpt-image-2')." },
+                "image": { "type": "string", "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')." },
                 "video": { "type": "string", "description": "Preferred video model (e.g., 'ltx23', 'wan22', 'seedance2')." },
                 "music": { "type": "string", "description": "Preferred music model." }
               }

package/manifests/generation-tools.json

@@ -1,5 +1,5 @@
 {
-  "version": "2026-04-27.1",
+  "version": "2026-08-14.1",
   "source": "sogni-creative-agent/src/tools/definitions/*/definition.ts",
   "schemaRefs": {
     "generate_image": "../schemas/tools/generate_image.schema.json",
@@ -46,8 +46,6 @@
                 "chroma-v46-flash",
                 "chroma1-hd",
                 "chroma-detail",
-                "flux1-krea",
-                "flux2",
                 "pony-v7",
                 "qwen-2512",
                 "qwen-2512-lightning",
@@ -65,15 +63,15 @@
                 "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 asks for a ChatGPT, OpenAI, GPT, GPT-2, GPT Image, or gpt-image-2 image/model, when they explicitly request very strong text rendering, or by default for 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-2\"/\"flux2\"/\"flux1-krea\"/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."
+              "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 asks for a ChatGPT, OpenAI, GPT, GPT-2, GPT Image, or gpt-image-2 image/model, when they explicitly request very strong text rendering, or by default for 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-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."
             },
             "width": {
               "type": "number",
-              "description": "Output image width in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"1080x1920\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+              "description": "Output image width in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"1080x1920\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
             },
             "height": {
               "type": "number",
-              "description": "Output image height in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"1080x1920\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+              "description": "Output image height in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"1080x1920\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
             },
             "numberOfVariations": {
               "type": "number",
@@ -177,9 +175,10 @@
                 "happyhorse-1.1-t2v",
                 "happyhorse-1.1-i2v",
                 "happyhorse-1.1-r2v",
-                "minimax-h3-r2v"
+                "minimax-h3-r2v",
+                "minimax-h3-r2v-turbo"
               ],
-              "description": "Video model. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx25\". HappyHorse 1.1 can be used here for \"happyhorse-1.1-t2v\" text-to-video, \"happyhorse-1.1-i2v\" with one uploaded/generated first-frame image via referenceImageIndices, or \"happyhorse-1.1-r2v\" with 1-9 image references. For a locked still image/source-frame animation, animate_photo with videoModel=\"happyhorse-1.1-i2v\" is also valid. HappyHorse supports 720p/1080p, 3-15s clips, native synchronized audio that is always on, image-only references, and no negativePrompt or generateAudio input. MiniMax H3 standard text-to-video uses \"minimax-h3-t2v\"; use \"minimax-h3-t2v-turbo\" for the 4-step Turbo tier. The Turbo image-to-video and first-to-last-frame selectors are \"minimax-h3-i2v-turbo\" and \"minimax-h3-flf2v-turbo\"; they keep H3's standard geometry, frame grid, and native-audio contract. There is no H3 Turbo r2v selector. H3 renders 5.17-15.08s clips at a fixed 24 fps inside a 1344x768 pixel budget on a 32px grid, jointly generates its own stereo audio, takes no negativePrompt input, and supports generateAudio=false to return a video without an audio track. MiniMax H3 reference-to-video uses \"minimax-h3-r2v\", a separate ref2va checkpoint and the only H3 mode that takes loose references: up to 9 reference images, 3 reference videos (24 fps, 2-15s, each with an optional soundtrack) and 3 standalone audio tracks, no more than 12 reference files in total, passed with referenceImageIndices/referenceVideoIndices/referenceAudioIndices. At least one visual reference is required: one or more images and/or videos. A video can be the only visual input; audio cannot be the sole input. H3 r2v references are NOT locked frames — name them in the prompt with H3's own 1-based per-type labels <Picture 1>/<Video 1>/<Audio 1> and give every one an explicit job (identity, style, camera movement, voice character), stating which reference wins when two disagree. Use animate_photo with \"minimax-h3-i2v\" for a first-frame animation or \"minimax-h3-flf2v\" with frameRole=\"both\" for a first-to-last-frame transition. Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance draft iteration unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" only when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for the full Seedance 2.0 model, explicit non-fast/full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft, Mini, or the fast model. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. Seedance supports multimodal loose reference assets. Seedance 2.0, Mini, and Fast accept images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset files total; Seedance 2.5 accepts images (up to 30), videos (up to 10), and audios (up to 10), with no more than 30 reference media files total. 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. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, and a much larger reference budget than Seedance 2.0: up to 30 images, 10 videos, and 10 audios, with no more than 30 reference media files in total. Seedance 2.5 covers text-to-video, image-to-video from a first frame, image-to-video with both a first and a last frame, and multimodal reference-to-video (including video editing and video extension). Pick \"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 natively instead of being split and stitched), or wants a first-and-last-frame Seedance transition. It does not replace \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance 2.5 is premium/subscriber-gated like the rest of the Seedance family."
+              "description": "Video model. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx25\". HappyHorse 1.1 can be used here for \"happyhorse-1.1-t2v\" text-to-video, \"happyhorse-1.1-i2v\" with one uploaded/generated first-frame image via referenceImageIndices, or \"happyhorse-1.1-r2v\" with 1-9 image references. For a locked still image/source-frame animation, animate_photo with videoModel=\"happyhorse-1.1-i2v\" is also valid. HappyHorse supports 720p/1080p, 3-15s clips, native synchronized audio that is always on, image-only references, and no negativePrompt or generateAudio input. MiniMax H3 standard text-to-video uses \"minimax-h3-t2v\"; use \"minimax-h3-t2v-turbo\" for the 4-step Turbo tier. The Turbo image-to-video and first-to-last-frame selectors are \"minimax-h3-i2v-turbo\" and \"minimax-h3-flf2v-turbo\"; they keep H3's standard geometry, frame grid, and native-audio contract. MiniMax H3 Ref2VA Turbo uses \"minimax-h3-r2v-turbo\", the dedicated four-step Euler/simple R2V tier with a 960x544 upstream-aligned default. H3 renders 5.17-15.08s clips at a fixed 24 fps inside a 1344x768 pixel budget on a 32px grid, jointly generates its own stereo audio, takes no negativePrompt input, and supports generateAudio=false to return a video without an audio track. MiniMax H3 reference-to-video uses \"minimax-h3-r2v\" for standard quality or \"minimax-h3-r2v-turbo\" for the dedicated four-step Turbo LoRA, a separate ref2va checkpoint and the only H3 mode that takes loose references: up to 9 reference images, 3 reference videos (24 fps, 2-15s, each with an optional soundtrack) and 3 standalone audio tracks, no more than 12 reference files in total, passed with referenceImageIndices/referenceVideoIndices/referenceAudioIndices. At least one visual reference is required: one or more images and/or videos. A video can be the only visual input; audio cannot be the sole input. H3 r2v references are NOT locked frames — name them in the prompt with H3's own 1-based per-type labels <Picture 1>/<Video 1>/<Audio 1> and give every one an explicit job (identity, style, camera movement, voice character), stating which reference wins when two disagree. Use animate_photo with \"minimax-h3-i2v\" for a first-frame animation or \"minimax-h3-flf2v\" with frameRole=\"both\" for a first-to-last-frame transition. Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance draft iteration unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" only when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for the full Seedance 2.0 model, explicit non-fast/full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft, Mini, or the fast model. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. Seedance supports multimodal loose reference assets. Seedance 2.0, Mini, and Fast accept images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset files total; Seedance 2.5 accepts images (up to 30), videos (up to 10), and audios (up to 10), with no more than 30 reference media files total. 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. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, and a much larger reference budget than Seedance 2.0: up to 30 images, 10 videos, and 10 audios, with no more than 30 reference media files in total. Seedance 2.5 covers text-to-video, image-to-video from a first frame, image-to-video with both a first and a last frame, and multimodal reference-to-video (including video editing and video extension). Pick \"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 natively instead of being split and stitched), or wants a first-and-last-frame Seedance transition. It does not replace \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance 2.5 is premium/subscriber-gated like the rest of the Seedance family."
             },
             "generateAudio": {
               "type": "boolean",
@@ -275,9 +274,10 @@
               "type": "string",
               "enum": [
                 "turbo",
-                "sft"
+                "sft",
+                "music3"
               ],
-              "description": "ACE-Step model variant. \"turbo\" (default): Higher quality audio generation with 4-16 steps and half the cost. Always use turbo unless the user explicitly requests the SFT model. \"sft\": Experimental model with lower audio quality but very strong lyric handling. 10-200 steps, full cost. Only use when the user specifically asks for SFT. Default: \"turbo\"."
+              "description": "Music model. \"turbo\" (default): ACE-Step 1.5 Turbo — fast 4-16 step drafts at half cost. \"sft\": ACE-Step 1.5 SFT — experimental, strong lyric handling, 10-200 steps, full cost. \"music3\": MiniMax Music 3 — premium autoregressive composer with the best vocals, lyric adherence and song structure; 30 steps, up to 5 minutes, ~20x turbo cost, and it treats duration as a ceiling (may end the song early at a musical resolution). Use music3 when the user asks for the best quality, realistic vocals, or full songs; otherwise default to \"turbo\"."
             },
             "timesig": {
               "type": "number",
@@ -306,7 +306,7 @@
       "type": "function",
       "function": {
         "name": "edit_image",
-        "description": "Generate images guided by reference photos. Supports GPT Image 2 up to 16 images, Flux.2 up to 6 images, Qwen up to 3 images, and Krea 2 Identity Edit / Dark Beast Krea 2 Identity Edit up to 2 images. Best for style-guided generation, combining elements from multiple images, ANY persona image creation, identity-preserving Krea edits, and any uploaded brand asset reuse — logos, brand marks, mascots, product shots, photos, screenshots, sketches, or character designs the user expects to appear in or guide the result. ALWAYS use this (never generate_image) when persona photos OR uploaded image assets meant for reuse are in context — even if a specific edit model is requested. Exception: explicit Z-image/Z-image Turbo/Krea 2 Turbo uploaded-image enhancement uses generate_image with sourceImageIndex and starting_image_strength because those base image-to-image models are not edit_image models. If a previous edit_image attempt did not preserve the uploaded asset well, stay on edit_image and tighten the prompt or switch model; generate_image has no access to the upload.",
+        "description": "Generate images guided by reference photos. Supports GPT Image 2 up to 16 images, Qwen up to 3 images, and Krea 2 Identity Edit / Dark Beast Krea 2 Identity Edit up to 2 images. Best for style-guided generation, combining elements from multiple images, ANY persona image creation, identity-preserving Krea edits, and any uploaded brand asset reuse — logos, brand marks, mascots, product shots, photos, screenshots, sketches, or character designs the user expects to appear in or guide the result. ALWAYS use this (never generate_image) when persona photos OR uploaded image assets meant for reuse are in context — even if a specific edit model is requested. Exception: explicit Z-image/Z-image Turbo/Krea 2 Turbo uploaded-image enhancement uses generate_image with sourceImageIndex and starting_image_strength because those base image-to-image models are not edit_image models. If a previous edit_image attempt did not preserve the uploaded asset well, stay on edit_image and tighten the prompt or switch model; generate_image has no access to the upload.",
         "parameters": {
           "type": "object",
           "properties": {
@@ -320,11 +320,10 @@
                 "gpt-image-2",
                 "qwen-lightning",
                 "qwen",
-                "flux2",
                 "krea-identity-edit",
                 "dark-beast-krea2-identity-edit"
               ],
-              "description": "The app auto-selects Fast→Qwen Lightning, HQ→full Qwen, and Pro→Flux.2 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 GPT/OpenAI/ChatGPT Image, or when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets may retain GPT Image 2. If GPT Image 2 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."
+              "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 GPT/OpenAI/ChatGPT Image, or when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets may retain GPT Image 2. If GPT Image 2 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."
             },
             "sourceImageIndex": {
               "type": "number",
@@ -338,11 +337,11 @@
             },
             "width": {
               "type": "number",
-              "description": "Output image width in pixels. Defaults to the context image width. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+              "description": "Output image width in pixels. Defaults to the context image width. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
             },
             "height": {
               "type": "number",
-              "description": "Output image height in pixels. Defaults to the context image height. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+              "description": "Output image height in pixels. Defaults to the context image height. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
             },
             "aspectRatio": {
               "type": "string",
@@ -542,7 +541,7 @@
                 "minimax-h3-flf2v",
                 "minimax-h3-flf2v-turbo"
               ],
-              "description": "Which video model to use. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2; per-clip duration 2-20s. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing; per-clip duration 2-20s. \"wan22\": Fast 4-step, simple motion, no audio; per-clip duration capped at 10s. \"happyhorse-1.1-i2v\": HappyHorse 1.1 image-to-video from one source frame; 3-15s, 720p/1080p, native synchronized audio always on. \"happyhorse-1.1-r2v\": HappyHorse 1.1 reference-to-video with image-only loose references; use only when referenceImageIndices provide additional image references for the same clip. \"minimax-h3-i2v\": MiniMax H3 image-to-video from one first frame; 5.17-15.08s at a fixed 24 fps with jointly generated stereo audio, a 1344x768 pixel budget on a 32px grid. \"minimax-h3-flf2v\": MiniMax H3 first-and-last-frame interpolation; use it with frameRole=\"both\" plus endImageIndex/endImageIndices so the first image is the opening frame and the second is the closing frame. Do not set seedance2, seedance2-mini, seedance2-fast, or seedance2-5 here; use generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text for Seedance. HappyHorse accepts neither negativePrompt nor generateAudio. MiniMax H3 accepts no negativePrompt; set generateAudio=false only when the user asks for silent output, and the returned video has no audio track. MiniMax H3 Base and Turbo T2V/I2V/FLF2V prompts use exactly integrated_multimodal_description, overall_soundscape, then non_diegetic_music; I2V/FLF2V prepend the official alignment line. Standard uses 20 steps with res_multistep/simple; Turbo uses 4 steps with er_sde/simple. Turbo is available only as minimax-h3-t2v-turbo, minimax-h3-i2v-turbo, and minimax-h3-flf2v-turbo; there is no Turbo R2V."
+              "description": "Which video model to use. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2; per-clip duration 2-20s. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing; per-clip duration 2-20s. \"wan22\": Fast 4-step, simple motion, no audio; per-clip duration capped at 10s. \"happyhorse-1.1-i2v\": HappyHorse 1.1 image-to-video from one source frame; 3-15s, 720p/1080p, native synchronized audio always on. \"happyhorse-1.1-r2v\": HappyHorse 1.1 reference-to-video with image-only loose references; use only when referenceImageIndices provide additional image references for the same clip. \"minimax-h3-i2v\": MiniMax H3 image-to-video from one first frame; 5.17-15.08s at a fixed 24 fps with jointly generated stereo audio, a 1344x768 pixel budget on a 32px grid. \"minimax-h3-flf2v\": MiniMax H3 first-and-last-frame interpolation; use it with frameRole=\"both\" plus endImageIndex/endImageIndices so the first image is the opening frame and the second is the closing frame. Do not set seedance2, seedance2-mini, seedance2-fast, or seedance2-5 here; use generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text for Seedance. HappyHorse accepts neither negativePrompt nor generateAudio. MiniMax H3 accepts no negativePrompt; set generateAudio=false only when the user asks for silent output, and the returned video has no audio track. MiniMax H3 Base and Turbo T2V/I2V/FLF2V prompts use exactly integrated_multimodal_description, overall_soundscape, then non_diegetic_music; I2V/FLF2V prepend the official alignment line. Standard uses 20 steps with res_multistep/simple; Turbo uses 4 steps with er_sde/simple. Turbo T2V/I2V/FLF2V use the selectors above; the dedicated Turbo R2V selector minimax-h3-r2v-turbo is intentionally routed through generate_video because it takes a loose multi-reference set rather than frame anchors."
             },
             "generateAudio": {
               "type": "boolean",

package/manifests/openai-tools.json

@@ -1,5 +1,5 @@
 {
-  "version": "2026-04-27.1",
+  "version": "2026-08-14.1",
   "source": "@sogni-ai/sogni-protocol hosted creative-tools surface (generation + composition)",
   "generatedAt": null,
   "tools": [
@@ -27,8 +27,6 @@
                 "chroma-v46-flash",
                 "chroma1-hd",
                 "chroma-detail",
-                "flux1-krea",
-                "flux2",
                 "pony-v7",
                 "qwen-2512",
                 "qwen-2512-lightning",
@@ -46,15 +44,15 @@
                 "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 asks for a ChatGPT, OpenAI, GPT, GPT-2, GPT Image, or gpt-image-2 image/model, when they explicitly request very strong text rendering, or by default for 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-2\"/\"flux2\"/\"flux1-krea\"/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."
+              "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 asks for a ChatGPT, OpenAI, GPT, GPT-2, GPT Image, or gpt-image-2 image/model, when they explicitly request very strong text rendering, or by default for 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-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."
             },
             "width": {
               "type": "number",
-              "description": "Output image width in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"1080x1920\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+              "description": "Output image width in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"1080x1920\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
             },
             "height": {
               "type": "number",
-              "description": "Output image height in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"1080x1920\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+              "description": "Output image height in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"1080x1920\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
             },
             "numberOfVariations": {
               "type": "number",
@@ -158,9 +156,10 @@
                 "happyhorse-1.1-t2v",
                 "happyhorse-1.1-i2v",
                 "happyhorse-1.1-r2v",
-                "minimax-h3-r2v"
+                "minimax-h3-r2v",
+                "minimax-h3-r2v-turbo"
               ],
-              "description": "Video model. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx25\". HappyHorse 1.1 can be used here for \"happyhorse-1.1-t2v\" text-to-video, \"happyhorse-1.1-i2v\" with one uploaded/generated first-frame image via referenceImageIndices, or \"happyhorse-1.1-r2v\" with 1-9 image references. For a locked still image/source-frame animation, animate_photo with videoModel=\"happyhorse-1.1-i2v\" is also valid. HappyHorse supports 720p/1080p, 3-15s clips, native synchronized audio that is always on, image-only references, and no negativePrompt or generateAudio input. MiniMax H3 standard text-to-video uses \"minimax-h3-t2v\"; use \"minimax-h3-t2v-turbo\" for the 4-step Turbo tier. The Turbo image-to-video and first-to-last-frame selectors are \"minimax-h3-i2v-turbo\" and \"minimax-h3-flf2v-turbo\"; they keep H3's standard geometry, frame grid, and native-audio contract. There is no H3 Turbo r2v selector. H3 renders 5.17-15.08s clips at a fixed 24 fps inside a 1344x768 pixel budget on a 32px grid, jointly generates its own stereo audio, takes no negativePrompt input, and supports generateAudio=false to return a video without an audio track. MiniMax H3 reference-to-video uses \"minimax-h3-r2v\", a separate ref2va checkpoint and the only H3 mode that takes loose references: up to 9 reference images, 3 reference videos (24 fps, 2-15s, each with an optional soundtrack) and 3 standalone audio tracks, no more than 12 reference files in total, passed with referenceImageIndices/referenceVideoIndices/referenceAudioIndices. At least one visual reference is required: one or more images and/or videos. A video can be the only visual input; audio cannot be the sole input. H3 r2v references are NOT locked frames — name them in the prompt with H3's own 1-based per-type labels <Picture 1>/<Video 1>/<Audio 1> and give every one an explicit job (identity, style, camera movement, voice character), stating which reference wins when two disagree. Use animate_photo with \"minimax-h3-i2v\" for a first-frame animation or \"minimax-h3-flf2v\" with frameRole=\"both\" for a first-to-last-frame transition. Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance draft iteration unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" only when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for the full Seedance 2.0 model, explicit non-fast/full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft, Mini, or the fast model. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. Seedance supports multimodal loose reference assets. Seedance 2.0, Mini, and Fast accept images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset files total; Seedance 2.5 accepts images (up to 30), videos (up to 10), and audios (up to 10), with no more than 30 reference media files total. 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. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, and a much larger reference budget than Seedance 2.0: up to 30 images, 10 videos, and 10 audios, with no more than 30 reference media files in total. Seedance 2.5 covers text-to-video, image-to-video from a first frame, image-to-video with both a first and a last frame, and multimodal reference-to-video (including video editing and video extension). Pick \"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 natively instead of being split and stitched), or wants a first-and-last-frame Seedance transition. It does not replace \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance 2.5 is premium/subscriber-gated like the rest of the Seedance family."
+              "description": "Video model. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx25\". HappyHorse 1.1 can be used here for \"happyhorse-1.1-t2v\" text-to-video, \"happyhorse-1.1-i2v\" with one uploaded/generated first-frame image via referenceImageIndices, or \"happyhorse-1.1-r2v\" with 1-9 image references. For a locked still image/source-frame animation, animate_photo with videoModel=\"happyhorse-1.1-i2v\" is also valid. HappyHorse supports 720p/1080p, 3-15s clips, native synchronized audio that is always on, image-only references, and no negativePrompt or generateAudio input. MiniMax H3 standard text-to-video uses \"minimax-h3-t2v\"; use \"minimax-h3-t2v-turbo\" for the 4-step Turbo tier. The Turbo image-to-video and first-to-last-frame selectors are \"minimax-h3-i2v-turbo\" and \"minimax-h3-flf2v-turbo\"; they keep H3's standard geometry, frame grid, and native-audio contract. MiniMax H3 Ref2VA Turbo uses \"minimax-h3-r2v-turbo\", the dedicated four-step Euler/simple R2V tier with a 960x544 upstream-aligned default. H3 renders 5.17-15.08s clips at a fixed 24 fps inside a 1344x768 pixel budget on a 32px grid, jointly generates its own stereo audio, takes no negativePrompt input, and supports generateAudio=false to return a video without an audio track. MiniMax H3 reference-to-video uses \"minimax-h3-r2v\" for standard quality or \"minimax-h3-r2v-turbo\" for the dedicated four-step Turbo LoRA, a separate ref2va checkpoint and the only H3 mode that takes loose references: up to 9 reference images, 3 reference videos (24 fps, 2-15s, each with an optional soundtrack) and 3 standalone audio tracks, no more than 12 reference files in total, passed with referenceImageIndices/referenceVideoIndices/referenceAudioIndices. At least one visual reference is required: one or more images and/or videos. A video can be the only visual input; audio cannot be the sole input. H3 r2v references are NOT locked frames — name them in the prompt with H3's own 1-based per-type labels <Picture 1>/<Video 1>/<Audio 1> and give every one an explicit job (identity, style, camera movement, voice character), stating which reference wins when two disagree. Use animate_photo with \"minimax-h3-i2v\" for a first-frame animation or \"minimax-h3-flf2v\" with frameRole=\"both\" for a first-to-last-frame transition. Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance draft iteration unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" only when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for the full Seedance 2.0 model, explicit non-fast/full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft, Mini, or the fast model. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. Seedance supports multimodal loose reference assets. Seedance 2.0, Mini, and Fast accept images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset files total; Seedance 2.5 accepts images (up to 30), videos (up to 10), and audios (up to 10), with no more than 30 reference media files total. 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. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, and a much larger reference budget than Seedance 2.0: up to 30 images, 10 videos, and 10 audios, with no more than 30 reference media files in total. Seedance 2.5 covers text-to-video, image-to-video from a first frame, image-to-video with both a first and a last frame, and multimodal reference-to-video (including video editing and video extension). Pick \"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 natively instead of being split and stitched), or wants a first-and-last-frame Seedance transition. It does not replace \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance 2.5 is premium/subscriber-gated like the rest of the Seedance family."
             },
             "generateAudio": {
               "type": "boolean",
@@ -256,9 +255,10 @@
               "type": "string",
               "enum": [
                 "turbo",
-                "sft"
+                "sft",
+                "music3"
               ],
-              "description": "ACE-Step model variant. \"turbo\" (default): Higher quality audio generation with 4-16 steps and half the cost. Always use turbo unless the user explicitly requests the SFT model. \"sft\": Experimental model with lower audio quality but very strong lyric handling. 10-200 steps, full cost. Only use when the user specifically asks for SFT. Default: \"turbo\"."
+              "description": "Music model. \"turbo\" (default): ACE-Step 1.5 Turbo — fast 4-16 step drafts at half cost. \"sft\": ACE-Step 1.5 SFT — experimental, strong lyric handling, 10-200 steps, full cost. \"music3\": MiniMax Music 3 — premium autoregressive composer with the best vocals, lyric adherence and song structure; 30 steps, up to 5 minutes, ~20x turbo cost, and it treats duration as a ceiling (may end the song early at a musical resolution). Use music3 when the user asks for the best quality, realistic vocals, or full songs; otherwise default to \"turbo\"."
             },
             "timesig": {
               "type": "number",
@@ -287,7 +287,7 @@
       "type": "function",
       "function": {
         "name": "edit_image",
-        "description": "Generate images guided by reference photos. Supports GPT Image 2 up to 16 images, Flux.2 up to 6 images, Qwen up to 3 images, and Krea 2 Identity Edit / Dark Beast Krea 2 Identity Edit up to 2 images. Best for style-guided generation, combining elements from multiple images, ANY persona image creation, identity-preserving Krea edits, and any uploaded brand asset reuse — logos, brand marks, mascots, product shots, photos, screenshots, sketches, or character designs the user expects to appear in or guide the result. ALWAYS use this (never generate_image) when persona photos OR uploaded image assets meant for reuse are in context — even if a specific edit model is requested. Exception: explicit Z-image/Z-image Turbo/Krea 2 Turbo uploaded-image enhancement uses generate_image with sourceImageIndex and starting_image_strength because those base image-to-image models are not edit_image models. If a previous edit_image attempt did not preserve the uploaded asset well, stay on edit_image and tighten the prompt or switch model; generate_image has no access to the upload.",
+        "description": "Generate images guided by reference photos. Supports GPT Image 2 up to 16 images, Qwen up to 3 images, and Krea 2 Identity Edit / Dark Beast Krea 2 Identity Edit up to 2 images. Best for style-guided generation, combining elements from multiple images, ANY persona image creation, identity-preserving Krea edits, and any uploaded brand asset reuse — logos, brand marks, mascots, product shots, photos, screenshots, sketches, or character designs the user expects to appear in or guide the result. ALWAYS use this (never generate_image) when persona photos OR uploaded image assets meant for reuse are in context — even if a specific edit model is requested. Exception: explicit Z-image/Z-image Turbo/Krea 2 Turbo uploaded-image enhancement uses generate_image with sourceImageIndex and starting_image_strength because those base image-to-image models are not edit_image models. If a previous edit_image attempt did not preserve the uploaded asset well, stay on edit_image and tighten the prompt or switch model; generate_image has no access to the upload.",
         "parameters": {
           "type": "object",
           "properties": {
@@ -301,11 +301,10 @@
                 "gpt-image-2",
                 "qwen-lightning",
                 "qwen",
-                "flux2",
                 "krea-identity-edit",
                 "dark-beast-krea2-identity-edit"
               ],
-              "description": "The app auto-selects Fast→Qwen Lightning, HQ→full Qwen, and Pro→Flux.2 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 GPT/OpenAI/ChatGPT Image, or when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets may retain GPT Image 2. If GPT Image 2 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."
+              "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 GPT/OpenAI/ChatGPT Image, or when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets may retain GPT Image 2. If GPT Image 2 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."
             },
             "sourceImageIndex": {
               "type": "number",
@@ -319,11 +318,11 @@
             },
             "width": {
               "type": "number",
-              "description": "Output image width in pixels. Defaults to the context image width. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+              "description": "Output image width in pixels. Defaults to the context image width. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
             },
             "height": {
               "type": "number",
-              "description": "Output image height in pixels. Defaults to the context image height. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+              "description": "Output image height in pixels. Defaults to the context image height. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
             },
             "aspectRatio": {
               "type": "string",
@@ -523,7 +522,7 @@
                 "minimax-h3-flf2v",
                 "minimax-h3-flf2v-turbo"
               ],
-              "description": "Which video model to use. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2; per-clip duration 2-20s. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing; per-clip duration 2-20s. \"wan22\": Fast 4-step, simple motion, no audio; per-clip duration capped at 10s. \"happyhorse-1.1-i2v\": HappyHorse 1.1 image-to-video from one source frame; 3-15s, 720p/1080p, native synchronized audio always on. \"happyhorse-1.1-r2v\": HappyHorse 1.1 reference-to-video with image-only loose references; use only when referenceImageIndices provide additional image references for the same clip. \"minimax-h3-i2v\": MiniMax H3 image-to-video from one first frame; 5.17-15.08s at a fixed 24 fps with jointly generated stereo audio, a 1344x768 pixel budget on a 32px grid. \"minimax-h3-flf2v\": MiniMax H3 first-and-last-frame interpolation; use it with frameRole=\"both\" plus endImageIndex/endImageIndices so the first image is the opening frame and the second is the closing frame. Do not set seedance2, seedance2-mini, seedance2-fast, or seedance2-5 here; use generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text for Seedance. HappyHorse accepts neither negativePrompt nor generateAudio. MiniMax H3 accepts no negativePrompt; set generateAudio=false only when the user asks for silent output, and the returned video has no audio track. MiniMax H3 Base and Turbo T2V/I2V/FLF2V prompts use exactly integrated_multimodal_description, overall_soundscape, then non_diegetic_music; I2V/FLF2V prepend the official alignment line. Standard uses 20 steps with res_multistep/simple; Turbo uses 4 steps with er_sde/simple. Turbo is available only as minimax-h3-t2v-turbo, minimax-h3-i2v-turbo, and minimax-h3-flf2v-turbo; there is no Turbo R2V."
+              "description": "Which video model to use. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2; per-clip duration 2-20s. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing; per-clip duration 2-20s. \"wan22\": Fast 4-step, simple motion, no audio; per-clip duration capped at 10s. \"happyhorse-1.1-i2v\": HappyHorse 1.1 image-to-video from one source frame; 3-15s, 720p/1080p, native synchronized audio always on. \"happyhorse-1.1-r2v\": HappyHorse 1.1 reference-to-video with image-only loose references; use only when referenceImageIndices provide additional image references for the same clip. \"minimax-h3-i2v\": MiniMax H3 image-to-video from one first frame; 5.17-15.08s at a fixed 24 fps with jointly generated stereo audio, a 1344x768 pixel budget on a 32px grid. \"minimax-h3-flf2v\": MiniMax H3 first-and-last-frame interpolation; use it with frameRole=\"both\" plus endImageIndex/endImageIndices so the first image is the opening frame and the second is the closing frame. Do not set seedance2, seedance2-mini, seedance2-fast, or seedance2-5 here; use generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text for Seedance. HappyHorse accepts neither negativePrompt nor generateAudio. MiniMax H3 accepts no negativePrompt; set generateAudio=false only when the user asks for silent output, and the returned video has no audio track. MiniMax H3 Base and Turbo T2V/I2V/FLF2V prompts use exactly integrated_multimodal_description, overall_soundscape, then non_diegetic_music; I2V/FLF2V prepend the official alignment line. Standard uses 20 steps with res_multistep/simple; Turbo uses 4 steps with er_sde/simple. Turbo T2V/I2V/FLF2V use the selectors above; the dedicated Turbo R2V selector minimax-h3-r2v-turbo is intentionally routed through generate_video because it takes a loose multi-reference set rather than frame anchors."
             },
             "generateAudio": {
               "type": "boolean",
@@ -1314,7 +1313,7 @@
             },
             "destination_model": {
               "type": "string",
-              "description": "Optional destination model selector, such as seedance2, ltx23, wan22, flux2, gpt-image-2, or sdxl."
+              "description": "Optional destination model selector, such as seedance2, ltx23, wan22, gpt-image-2, or sdxl."
             },
             "destination_tool": {
               "type": "string",
@@ -1618,7 +1617,7 @@
               "properties": {
                 "image": {
                   "type": "string",
-                  "description": "Preferred image model (e.g., 'flux2', 'gpt-image-2')."
+                  "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')."
                 },
                 "video": {
                   "type": "string",
@@ -1821,7 +1820,7 @@
               "properties": {
                 "image": {
                   "type": "string",
-                  "description": "Preferred image model (e.g., 'flux2', 'gpt-image-2')."
+                  "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')."
                 },
                 "video": {
                   "type": "string",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sogni-ai/sogni-protocol",
-  "version": "1.0.0-alpha.19",
+  "version": "1.0.0-alpha.20",
   "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/compose_workflow.json

@@ -9,7 +9,7 @@
     "duration_seconds": "Target total duration in seconds for video-bearing plans (1-120).",
     "aspect_ratio": "Output aspect ratio. One of 1:1, 4:3, 3:4, 16:9, 9:16, 21:9.",
     "style": "Optional stylistic guidance such as \"cinematic, neon, low-key\" or \"whiteboard illustration\".",
-    "destination_models": "Optional preferred image/video/music model selectors (e.g. flux2, ltx25, ltx23). Each subkey is optional.",
+    "destination_models": "Optional preferred image/video/music model selectors (e.g. gpt-image-2, ltx25, ltx23). Each subkey is optional.",
     "max_estimated_capacity_units": "Optional coarse capacity budget. If set, the planner tries to keep total estimated cost at or below this value; the API returns fits_budget=false if it cannot.",
     "include_audio": "When true, include a generate_music step in the plan. Defaults to false.",
     "return_format": "Reserved for future use; only \"json\" is supported in Phase 1. Omit if unsure."

package/prompts/tools/compose_workflow_template.json

@@ -14,7 +14,7 @@
     "duration_seconds": "Target total duration in seconds for video-bearing plans (1-120).",
     "aspect_ratio": "Output aspect ratio. One of 1:1, 4:3, 3:4, 16:9, 9:16, 21:9.",
     "style": "Optional stylistic guidance such as \"cinematic, neon, low-key\" or \"whiteboard illustration\".",
-    "destination_models": "Optional preferred image/video/music model selectors (e.g. flux2, ltx25, ltx23). Each subkey is optional.",
+    "destination_models": "Optional preferred image/video/music model selectors (e.g. gpt-image-2, ltx25, ltx23). Each subkey is optional.",
     "max_estimated_capacity_units": "Optional coarse capacity budget. The planner returns fits_budget=false if it cannot fit under the cap.",
     "include_audio": "When true, include a generate_music step in the example plan. Defaults to false.",
     "return_format": "Reserved for future use; only \"json\" is supported in Phase 2. Omit if unsure.",

package/prompts/tools/enhance_prompt.json

@@ -6,7 +6,7 @@
   "parameterDocs": {
     "prompt": "The source prompt, rough idea, or prompt revision request to enhance.",
     "target_output": "The kind of prompt artifact to produce. One of image_prompt, video_prompt, music_prompt, edit_prompt, model_prompt, or general_prompt.",
-    "destination_model": "Optional destination model selector, such as seedance2, ltx25, ltx23, wan22, flux2, gpt-image-2, or sdxl.",
+    "destination_model": "Optional destination model selector, such as seedance2, ltx25, ltx23, wan22, gpt-image-2, or sdxl.",
     "destination_tool": "Optional downstream generation tool, such as generate_image, edit_image, generate_video, animate_photo, sound_to_video, video_to_video, or generate_music.",
     "prompting_type": "Optional image-prompting family when producing an image prompt. One of flux, sdxl, sd15, pony, fast, sd3, editing, or video.",
     "model_title": "Optional human-readable target model name for image prompt guidance.",

package/prompts/tools/generate_image.json

@@ -2,9 +2,9 @@
   "contractId": "generate_image_v1",
   "version": "1.1.0",
   "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\nFLUX.2 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.",
+  "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.",
   "parameterDocs": {
-    "prompt": "Text description. Follow FLUX.2 prompt order: subject first. Use Dynamic Prompt syntax when numberOfVariations > 1.",
+    "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.",
     "aspectRatio": "For ordinary images feeding a video tool, set to match the target video aspect ratio. For composite GPT Image 2 storyboard sheets, default the sheet pixel dimensions to a balanced grid that hosts the target cell aspect natively (portrait video target -> portrait/square sheet, landscape video target -> landscape sheet) unless the user explicitly specifies a storyboard page/canvas/sheet shape; keep the target video ratio inside each frame area."
   }

package/schemas/tools/animate_photo.schema.json

@@ -32,7 +32,7 @@
         "minimax-h3-flf2v",
         "minimax-h3-flf2v-turbo"
       ],
-      "description": "Which video model to use. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2; per-clip duration 2-20s. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing; per-clip duration 2-20s. \"wan22\": Fast 4-step, simple motion, no audio; per-clip duration capped at 10s. \"happyhorse-1.1-i2v\": HappyHorse 1.1 image-to-video from one source frame; 3-15s, 720p/1080p, native synchronized audio always on. \"happyhorse-1.1-r2v\": HappyHorse 1.1 reference-to-video with image-only loose references; use only when referenceImageIndices provide additional image references for the same clip. \"minimax-h3-i2v\": MiniMax H3 image-to-video from one first frame; 5.17-15.08s at a fixed 24 fps with jointly generated stereo audio, a 1344x768 pixel budget on a 32px grid. \"minimax-h3-flf2v\": MiniMax H3 first-and-last-frame interpolation; use it with frameRole=\"both\" plus endImageIndex/endImageIndices so the first image is the opening frame and the second is the closing frame. Do not set seedance2, seedance2-mini, seedance2-fast, or seedance2-5 here; use generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text for Seedance. HappyHorse accepts neither negativePrompt nor generateAudio. MiniMax H3 accepts no negativePrompt; set generateAudio=false only when the user asks for silent output, and the returned video has no audio track. MiniMax H3 Base and Turbo T2V/I2V/FLF2V prompts use exactly integrated_multimodal_description, overall_soundscape, then non_diegetic_music; I2V/FLF2V prepend the official alignment line. Standard uses 20 steps with res_multistep/simple; Turbo uses 4 steps with er_sde/simple. Turbo is available only as minimax-h3-t2v-turbo, minimax-h3-i2v-turbo, and minimax-h3-flf2v-turbo; there is no Turbo R2V."
+      "description": "Which video model to use. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2; per-clip duration 2-20s. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing; per-clip duration 2-20s. \"wan22\": Fast 4-step, simple motion, no audio; per-clip duration capped at 10s. \"happyhorse-1.1-i2v\": HappyHorse 1.1 image-to-video from one source frame; 3-15s, 720p/1080p, native synchronized audio always on. \"happyhorse-1.1-r2v\": HappyHorse 1.1 reference-to-video with image-only loose references; use only when referenceImageIndices provide additional image references for the same clip. \"minimax-h3-i2v\": MiniMax H3 image-to-video from one first frame; 5.17-15.08s at a fixed 24 fps with jointly generated stereo audio, a 1344x768 pixel budget on a 32px grid. \"minimax-h3-flf2v\": MiniMax H3 first-and-last-frame interpolation; use it with frameRole=\"both\" plus endImageIndex/endImageIndices so the first image is the opening frame and the second is the closing frame. Do not set seedance2, seedance2-mini, seedance2-fast, or seedance2-5 here; use generate_video with referenceImageIndices/referenceVideoIndices/referenceAudioIndices and @Image/@Video/@Audio role text for Seedance. HappyHorse accepts neither negativePrompt nor generateAudio. MiniMax H3 accepts no negativePrompt; set generateAudio=false only when the user asks for silent output, and the returned video has no audio track. MiniMax H3 Base and Turbo T2V/I2V/FLF2V prompts use exactly integrated_multimodal_description, overall_soundscape, then non_diegetic_music; I2V/FLF2V prepend the official alignment line. Standard uses 20 steps with res_multistep/simple; Turbo uses 4 steps with er_sde/simple. Turbo T2V/I2V/FLF2V use the selectors above; the dedicated Turbo R2V selector minimax-h3-r2v-turbo is intentionally routed through generate_video because it takes a loose multi-reference set rather than frame anchors."
     },
     "generateAudio": {
       "type": "boolean",

package/schemas/tools/compose_workflow.schema.json

@@ -37,7 +37,7 @@
       "properties": {
         "image": {
           "type": "string",
-          "description": "Preferred image model (e.g., 'flux2', 'gpt-image-2')."
+          "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')."
         },
         "video": {
           "type": "string",

package/schemas/tools/compose_workflow_template.schema.json

@@ -116,7 +116,7 @@
       "type": "object",
       "additionalProperties": false,
       "properties": {
-        "image": { "type": "string", "description": "Preferred image model (e.g., 'flux2', 'gpt-image-2')." },
+        "image": { "type": "string", "description": "Preferred image model (e.g., 'gpt-image-2', 'qwen')." },
         "video": { "type": "string", "description": "Preferred video model (e.g., 'ltx25', 'ltx23', 'wan22', 'seedance2')." },
         "music": { "type": "string", "description": "Preferred music model." }
       }

package/schemas/tools/edit_image.schema.json

@@ -3,7 +3,7 @@
   "$id": "https://schemas.sogni.ai/creative-agent/2026-07-18.1/tools/edit_image.schema.json",
   "title": "edit_image arguments",
   "schemaVersion": "2026-07-18.1",
-  "description": "Generate images guided by reference photos. Supports GPT Image 2 up to 16 images, Flux.2 up to 6 images, Qwen up to 3 images, and Krea 2 Identity Edit / Dark Beast Krea 2 Identity Edit up to 2 images. Best for style-guided generation, combining elements from multiple images, ANY persona image creation, identity-preserving Krea edits, and any uploaded brand asset reuse — logos, brand marks, mascots, product shots, photos, screenshots, sketches, or character designs the user expects to appear in or guide the result. ALWAYS use this (never generate_image) when persona photos OR uploaded image assets meant for reuse are in context — even if a specific edit model is requested. Exception: explicit Z-image/Z-image Turbo/Krea 2 Turbo uploaded-image enhancement uses generate_image with sourceImageIndex and starting_image_strength because those base image-to-image models are not edit_image models. If a previous edit_image attempt did not preserve the uploaded asset well, stay on edit_image and tighten the prompt or switch model; generate_image has no access to the upload.",
+  "description": "Generate images guided by reference photos. Supports GPT Image 2 up to 16 images, Qwen up to 3 images, and Krea 2 Identity Edit / Dark Beast Krea 2 Identity Edit up to 2 images. Best for style-guided generation, combining elements from multiple images, ANY persona image creation, identity-preserving Krea edits, and any uploaded brand asset reuse — logos, brand marks, mascots, product shots, photos, screenshots, sketches, or character designs the user expects to appear in or guide the result. ALWAYS use this (never generate_image) when persona photos OR uploaded image assets meant for reuse are in context — even if a specific edit model is requested. Exception: explicit Z-image/Z-image Turbo/Krea 2 Turbo uploaded-image enhancement uses generate_image with sourceImageIndex and starting_image_strength because those base image-to-image models are not edit_image models. If a previous edit_image attempt did not preserve the uploaded asset well, stay on edit_image and tighten the prompt or switch model; generate_image has no access to the upload.",
   "type": "object",
   "additionalProperties": false,
   "properties": {
@@ -17,11 +17,10 @@
         "gpt-image-2",
         "qwen-lightning",
         "qwen",
-        "flux2",
         "krea-identity-edit",
         "dark-beast-krea2-identity-edit"
       ],
-      "description": "The app auto-selects Fast→Qwen Lightning, HQ→full Qwen, and Pro→Flux.2 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 GPT/OpenAI/ChatGPT Image, or when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets may retain GPT Image 2. If GPT Image 2 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."
+      "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 GPT/OpenAI/ChatGPT Image, or when precise typography, dense labels, or a professional multi-panel layout is the primary requirement; Pro character sheets may retain GPT Image 2. If GPT Image 2 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."
     },
     "sourceImageIndex": {
       "type": "number",
@@ -35,11 +34,11 @@
     },
     "width": {
       "type": "number",
-      "description": "Output image width in pixels. Defaults to the context image width. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+      "description": "Output image width in pixels. Defaults to the context image width. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
     },
     "height": {
       "type": "number",
-      "description": "Output image height in pixels. Defaults to the context image height. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+      "description": "Output image height in pixels. Defaults to the context image height. Supported bounds depend on the selected edit model: Qwen edit models support 256-2560 on either edge; Krea 2 Identity Edit and Dark Beast Krea 2 Identity Edit work best from 512-2048 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
     },
     "aspectRatio": {
       "type": "string",

package/schemas/tools/enhance_prompt.schema.json

@@ -17,7 +17,7 @@
     },
     "destination_model": {
       "type": "string",
-      "description": "Optional destination model selector, such as seedance2, ltx25, ltx23, wan22, flux2, gpt-image-2, or sdxl."
+      "description": "Optional destination model selector, such as seedance2, ltx25, ltx23, wan22, gpt-image-2, or sdxl."
     },
     "destination_tool": {
       "type": "string",

package/schemas/tools/generate_image.schema.json

@@ -23,8 +23,6 @@
         "chroma-v46-flash",
         "chroma1-hd",
         "chroma-detail",
-        "flux1-krea",
-        "flux2",
         "pony-v7",
         "qwen-2512",
         "qwen-2512-lightning",
@@ -42,15 +40,15 @@
         "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 asks for a ChatGPT, OpenAI, GPT, GPT-2, GPT Image, or gpt-image-2 image/model, when they explicitly request very strong text rendering, or by default for 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-2\"/\"flux2\"/\"flux1-krea\"/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."
+      "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 asks for a ChatGPT, OpenAI, GPT, GPT-2, GPT Image, or gpt-image-2 image/model, when they explicitly request very strong text rendering, or by default for 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-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."
     },
     "width": {
       "type": "number",
-      "description": "Output image width in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"1080x1920\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+      "description": "Output image width in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a width, exact pixel dimensions, or a named resolution (e.g., \"1280 wide\", \"1280x720\", \"720p\", \"1080x1920\", \"3840x2160\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
     },
     "height": {
       "type": "number",
-      "description": "Output image height in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; Flux.2 uses a 2048x2048 total pixel budget (4,194,304 pixels) with non-square edges up to 2816, such as 1408x2816; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"1080x1920\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
+      "description": "Output image height in pixels. Default: 1024. Supported bounds depend on the selected image model: Z-Image/Z-Image Turbo, Dark Beast Z-Image Turbo, Chroma, and legacy/specialized image models support 256-2048 on either edge; Krea 2 Turbo, Dark Beast KREA 2, and Qwen image models support 256-2560 on either edge; One Obsession v22 supports 256-1920 on either edge; GPT Image 2 supports flexible dimensions up to 3840px on either edge with max 3:1 aspect ratio and a total pixel budget from 655,360 to 8,294,400. Set when the user specifies a height, exact pixel dimensions, or a named resolution (e.g., \"720 high\", \"1280x720\", \"720p\", \"1080x1920\", \"2160x3840\"). If the user gives only one dimension, set only that dimension and preserve/infer the sensible aspect ratio. User-requested dimensions override the default media quality, including Pro. Non-multiple-of-16 values are accepted when in bounds; the renderer snaps to the nearest supported size internally, so do not ask the user to adjust by a few pixels."
     },
     "numberOfVariations": {
       "type": "number",

package/schemas/tools/generate_music.schema.json

@@ -35,9 +35,10 @@
       "type": "string",
       "enum": [
         "turbo",
-        "sft"
+        "sft",
+        "music3"
       ],
-      "description": "ACE-Step model variant. \"turbo\" (default): Higher quality audio generation with 4-16 steps and half the cost. Always use turbo unless the user explicitly requests the SFT model. \"sft\": Experimental model with lower audio quality but very strong lyric handling. 10-200 steps, full cost. Only use when the user specifically asks for SFT. Default: \"turbo\"."
+      "description": "Music model. \"turbo\" (default): ACE-Step 1.5 Turbo — fast 4-16 step drafts at half cost. \"sft\": ACE-Step 1.5 SFT — experimental, strong lyric handling, 10-200 steps, full cost. \"music3\": MiniMax Music 3 — premium autoregressive composer with the best vocals, lyric adherence and song structure; 30 steps, up to 5 minutes, ~20x turbo cost, and it treats duration as a ceiling (may end the song early at a musical resolution). Use music3 when the user asks for the best quality, realistic vocals, or full songs; otherwise default to \"turbo\"."
     },
     "timesig": {
       "type": "number",

package/schemas/tools/generate_video.schema.json

@@ -44,9 +44,10 @@
         "happyhorse-1.1-t2v",
         "happyhorse-1.1-i2v",
         "happyhorse-1.1-r2v",
-        "minimax-h3-r2v"
+        "minimax-h3-r2v",
+        "minimax-h3-r2v-turbo"
       ],
-      "description": "Video model. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx25\". HappyHorse 1.1 can be used here for \"happyhorse-1.1-t2v\" text-to-video, \"happyhorse-1.1-i2v\" with one uploaded/generated first-frame image via referenceImageIndices, or \"happyhorse-1.1-r2v\" with 1-9 image references. For a locked still image/source-frame animation, animate_photo with videoModel=\"happyhorse-1.1-i2v\" is also valid. HappyHorse supports 720p/1080p, 3-15s clips, native synchronized audio that is always on, image-only references, and no negativePrompt or generateAudio input. MiniMax H3 standard text-to-video uses \"minimax-h3-t2v\"; use \"minimax-h3-t2v-turbo\" for the 4-step Turbo tier. The Turbo image-to-video and first-to-last-frame selectors are \"minimax-h3-i2v-turbo\" and \"minimax-h3-flf2v-turbo\"; they keep H3's standard geometry, frame grid, and native-audio contract. There is no H3 Turbo r2v selector. H3 renders 5.17-15.08s clips at a fixed 24 fps inside a 1344x768 pixel budget on a 32px grid, jointly generates its own stereo audio, takes no negativePrompt input, and supports generateAudio=false to return a video without an audio track. MiniMax H3 reference-to-video uses \"minimax-h3-r2v\", a separate ref2va checkpoint and the only H3 mode that takes loose references: up to 9 reference images, 3 reference videos (24 fps, 2-15s, each with an optional soundtrack) and 3 standalone audio tracks, no more than 12 reference files in total, passed with referenceImageIndices/referenceVideoIndices/referenceAudioIndices. At least one visual reference is required: one or more images and/or videos. A video can be the only visual input; audio cannot be the sole input. H3 r2v references are NOT locked frames — name them in the prompt with H3's own 1-based per-type labels <Picture 1>/<Video 1>/<Audio 1> and give every one an explicit job (identity, style, camera movement, voice character), stating which reference wins when two disagree. Use animate_photo with \"minimax-h3-i2v\" for a first-frame animation or \"minimax-h3-flf2v\" with frameRole=\"both\" for a first-to-last-frame transition. Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance draft iteration unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" only when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for the full Seedance 2.0 model, explicit non-fast/full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft, Mini, or the fast model. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. Seedance supports multimodal loose reference assets. Seedance 2.0, Mini, and Fast accept images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset files total; Seedance 2.5 accepts images (up to 30), videos (up to 10), and audios (up to 10), with no more than 30 reference media files total. 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. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, and a much larger reference budget than Seedance 2.0: up to 30 images, 10 videos, and 10 audios, with no more than 30 reference media files in total. Seedance 2.5 covers text-to-video, image-to-video from a first frame, image-to-video with both a first and a last frame, and multimodal reference-to-video (including video editing and video extension). Pick \"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 natively instead of being split and stitched), or wants a first-and-last-frame Seedance transition. It does not replace \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance 2.5 is premium/subscriber-gated like the rest of the Seedance family."
+      "description": "Video model. \"ltx25\" (default): LTX 2.5 with native audio; Fast/HQ use the official distilled INT8 workflow and Pro uses dev INT8 with the required official distilled Speed LoRA in stage 2. \"ltx23\": LTX 2.3 rollback with its existing distilled/dev quality routing. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx25\". HappyHorse 1.1 can be used here for \"happyhorse-1.1-t2v\" text-to-video, \"happyhorse-1.1-i2v\" with one uploaded/generated first-frame image via referenceImageIndices, or \"happyhorse-1.1-r2v\" with 1-9 image references. For a locked still image/source-frame animation, animate_photo with videoModel=\"happyhorse-1.1-i2v\" is also valid. HappyHorse supports 720p/1080p, 3-15s clips, native synchronized audio that is always on, image-only references, and no negativePrompt or generateAudio input. MiniMax H3 standard text-to-video uses \"minimax-h3-t2v\"; use \"minimax-h3-t2v-turbo\" for the 4-step Turbo tier. The Turbo image-to-video and first-to-last-frame selectors are \"minimax-h3-i2v-turbo\" and \"minimax-h3-flf2v-turbo\"; they keep H3's standard geometry, frame grid, and native-audio contract. MiniMax H3 Ref2VA Turbo uses \"minimax-h3-r2v-turbo\", the dedicated four-step Euler/simple R2V tier with a 960x544 upstream-aligned default. H3 renders 5.17-15.08s clips at a fixed 24 fps inside a 1344x768 pixel budget on a 32px grid, jointly generates its own stereo audio, takes no negativePrompt input, and supports generateAudio=false to return a video without an audio track. MiniMax H3 reference-to-video uses \"minimax-h3-r2v\" for standard quality or \"minimax-h3-r2v-turbo\" for the dedicated four-step Turbo LoRA, a separate ref2va checkpoint and the only H3 mode that takes loose references: up to 9 reference images, 3 reference videos (24 fps, 2-15s, each with an optional soundtrack) and 3 standalone audio tracks, no more than 12 reference files in total, passed with referenceImageIndices/referenceVideoIndices/referenceAudioIndices. At least one visual reference is required: one or more images and/or videos. A video can be the only visual input; audio cannot be the sole input. H3 r2v references are NOT locked frames — name them in the prompt with H3's own 1-based per-type labels <Picture 1>/<Video 1>/<Audio 1> and give every one an explicit job (identity, style, camera movement, voice character), stating which reference wins when two disagree. Use animate_photo with \"minimax-h3-i2v\" for a first-frame animation or \"minimax-h3-flf2v\" with frameRole=\"both\" for a first-to-last-frame transition. Seedance quality is selected only by model: use \"seedance2-mini\" for fast, lower-cost 720p Seedance draft iteration unless the user explicitly asks for legacy Fast, use \"seedance2-fast\" only when the user asks for Seedance Fast / seedance-fast, and use \"seedance2\" for the full Seedance 2.0 model, explicit non-fast/full-quality requests, 1080p/4K requests, or generated/uploaded storyboard images unless the user explicitly asks for a draft, Mini, or the fast model. Do not use Default Media Quality Fast/HQ/Pro or targetResolution to represent Seedance quality. Seedance supports multimodal loose reference assets. Seedance 2.0, Mini, and Fast accept images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset files total; Seedance 2.5 accepts images (up to 30), videos (up to 10), and audios (up to 10), with no more than 30 reference media files total. 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. \"seedance2-5\": Seedance 2.5, the newest Seedance generation — 480p and 720p ONLY (it cannot render 1080p or 4K), 4-30s per clip at a fixed 24 fps, native audio, and a much larger reference budget than Seedance 2.0: up to 30 images, 10 videos, and 10 audios, with no more than 30 reference media files in total. Seedance 2.5 covers text-to-video, image-to-video from a first frame, image-to-video with both a first and a last frame, and multimodal reference-to-video (including video editing and video extension). Pick \"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 natively instead of being split and stitched), or wants a first-and-last-frame Seedance transition. It does not replace \"seedance2\" for 1080p/4K requests, which Seedance 2.5 cannot satisfy. Seedance 2.5 is premium/subscriber-gated like the rest of the Seedance family."
     },
     "generateAudio": {
       "type": "boolean",

package/version.json

@@ -1,4 +1,4 @@
 {
-  "protocolVersion": "1.11.0",
+  "protocolVersion": "1.12.0",
   "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."
 }