@sogni-ai/sogni-intelligence-client 3.11.0 → 3.12.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/media/videoSettings.d.ts +9 -1
- package/dist/media/videoSettings.d.ts.map +1 -1
- package/dist/media/videoSettings.js +92 -6
- package/dist/media/videoSettings.js.map +1 -1
- package/dist/openai-tools/_manifests.generated.d.ts.map +1 -1
- package/dist/openai-tools/_manifests.generated.js +24 -12
- package/dist/openai-tools/_manifests.generated.js.map +1 -1
- package/dist/openai-tools/generation-tools.json +24 -12
- package/dist/schemas/tools/animate_photo.schema.json +12 -4
- package/dist/schemas/tools/generate_video.schema.json +9 -5
- package/dist/schemas/tools/sound_to_video.schema.json +2 -2
- package/dist/schemas/tools/video_to_video.schema.json +1 -1
- package/dist/tools/definitions/animate-photo/definition.d.ts.map +1 -1
- package/dist/tools/definitions/animate-photo/definition.js +9 -5
- package/dist/tools/definitions/animate-photo/definition.js.map +1 -1
- package/dist/tools/definitions/generate-video/definition.d.ts.map +1 -1
- package/dist/tools/definitions/generate-video/definition.js +4 -3
- package/dist/tools/definitions/generate-video/definition.js.map +1 -1
- package/dist/tools/definitions/sound-to-video/definition.js +1 -1
- package/dist/tools/definitions/sound-to-video/definition.js.map +1 -1
- package/dist/tools/definitions/video-to-video/definition.js +1 -1
- package/dist/tools/definitions/video-to-video/definition.js.map +1 -1
- package/dist/tools/shared/modelRegistry.d.ts.map +1 -1
- package/dist/tools/shared/modelRegistry.js +3 -0
- package/dist/tools/shared/modelRegistry.js.map +1 -1
- package/dist-esm/media/videoSettings.js +92 -6
- package/dist-esm/media/videoSettings.js.map +1 -1
- package/dist-esm/openai-tools/_manifests.generated.js +24 -12
- package/dist-esm/openai-tools/_manifests.generated.js.map +1 -1
- package/dist-esm/openai-tools/generation-tools.json +24 -12
- package/dist-esm/schemas/tools/animate_photo.schema.json +12 -4
- package/dist-esm/schemas/tools/generate_video.schema.json +9 -5
- package/dist-esm/schemas/tools/sound_to_video.schema.json +2 -2
- package/dist-esm/schemas/tools/video_to_video.schema.json +1 -1
- package/dist-esm/tools/definitions/animate-photo/definition.js +9 -5
- package/dist-esm/tools/definitions/animate-photo/definition.js.map +1 -1
- package/dist-esm/tools/definitions/generate-video/definition.js +4 -3
- package/dist-esm/tools/definitions/generate-video/definition.js.map +1 -1
- package/dist-esm/tools/definitions/sound-to-video/definition.js +1 -1
- package/dist-esm/tools/definitions/sound-to-video/definition.js.map +1 -1
- package/dist-esm/tools/definitions/video-to-video/definition.js +1 -1
- package/dist-esm/tools/definitions/video-to-video/definition.js.map +1 -1
- package/dist-esm/tools/shared/modelRegistry.js +3 -0
- package/dist-esm/tools/shared/modelRegistry.js.map +1 -1
- package/package.json +3 -3
|
@@ -154,13 +154,13 @@
|
|
|
154
154
|
},
|
|
155
155
|
"duration": {
|
|
156
156
|
"type": "number",
|
|
157
|
-
"description": "Video duration in seconds. Default: 5. Range: 2-20. Use when the user explicitly requests a specific length.",
|
|
157
|
+
"description": "Video duration in seconds. Default: 5. Range: 2-20. Use when the user explicitly requests a specific length. MiniMax H3 is quantized to a 17-frame grid at a fixed 24 fps and renders 124-362 frames, so an H3 clip runs 5.17-15.08 seconds and a requested length outside that window snaps to the nearest valid H3 length.",
|
|
158
158
|
"minimum": 2,
|
|
159
159
|
"maximum": 20
|
|
160
160
|
},
|
|
161
161
|
"negativePrompt": {
|
|
162
162
|
"type": "string",
|
|
163
|
-
"description": "
|
|
163
|
+
"description": "Advanced LTX/WAN only. Use this field only when the user explicitly asks to set a separate negative prompt. MiniMax H3 has no negative-prompt input; put requested exclusions in prompt. Do not set for MiniMax H3, Seedance, or HappyHorse."
|
|
164
164
|
},
|
|
165
165
|
"videoModel": {
|
|
166
166
|
"type": "string",
|
|
@@ -169,13 +169,17 @@
|
|
|
169
169
|
"wan22",
|
|
170
170
|
"seedance2",
|
|
171
171
|
"seedance2-mini",
|
|
172
|
-
"seedance2-fast"
|
|
172
|
+
"seedance2-fast",
|
|
173
|
+
"minimax-h3-t2v",
|
|
174
|
+
"happyhorse-1.1-t2v",
|
|
175
|
+
"happyhorse-1.1-i2v",
|
|
176
|
+
"happyhorse-1.1-r2v"
|
|
173
177
|
],
|
|
174
|
-
"description": "Video model. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step
|
|
178
|
+
"description": "Video model. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx23\". 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 text-to-video uses \"minimax-h3-t2v\". 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. 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: images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset 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."
|
|
175
179
|
},
|
|
176
180
|
"generateAudio": {
|
|
177
181
|
"type": "boolean",
|
|
178
|
-
"description": "
|
|
182
|
+
"description": "Whether to include generated/native audio for audio-capable models. Omit to include audio by default; set false only when the user explicitly asks for silent output or no audio. When false, the returned video has no audio track. Not supported by WAN or HappyHorse."
|
|
179
183
|
},
|
|
180
184
|
"referenceImageIndices": {
|
|
181
185
|
"type": "array",
|
|
@@ -525,17 +529,25 @@
|
|
|
525
529
|
"type": "string",
|
|
526
530
|
"enum": [
|
|
527
531
|
"ltx23",
|
|
528
|
-
"wan22"
|
|
532
|
+
"wan22",
|
|
533
|
+
"happyhorse-1.1-i2v",
|
|
534
|
+
"happyhorse-1.1-r2v",
|
|
535
|
+
"minimax-h3-i2v",
|
|
536
|
+
"minimax-h3-flf2v"
|
|
529
537
|
],
|
|
530
|
-
"description": "Which video model to use. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step
|
|
538
|
+
"description": "Which video model to use. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant; 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, or seedance2-fast 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."
|
|
539
|
+
},
|
|
540
|
+
"generateAudio": {
|
|
541
|
+
"type": "boolean",
|
|
542
|
+
"description": "Whether to include generated/native audio for audio-capable models. Omit to include audio by default; set false only when the user explicitly asks for silent output or no audio. When false, the returned video has no audio track. Ignored by audio-less WAN."
|
|
531
543
|
},
|
|
532
544
|
"negativePrompt": {
|
|
533
545
|
"type": "string",
|
|
534
|
-
"description": "
|
|
546
|
+
"description": "Advanced LTX/WAN only. Use this field only when the user explicitly asks to set a separate negative prompt. MiniMax H3 has no negative-prompt input; put requested exclusions in prompt."
|
|
535
547
|
},
|
|
536
548
|
"duration": {
|
|
537
549
|
"type": "number",
|
|
538
|
-
"description": "Video duration in seconds. Default: 5. Use when the user explicitly requests a specific length (e.g., \"make a 10 second video\"). Per-model maximum: ltx23 = 20s, wan22 = 10s (
|
|
550
|
+
"description": "Video duration in seconds. Default: 5. Use when the user explicitly requests a specific length (e.g., \"make a 10 second video\"). Per-model maximum: ltx23 = 20s, wan22 = 10s (clips longer than this are invalid), minimax-h3 = 15.08s with a 5.17s minimum because H3 renders 124-362 frames on a 17-frame grid at a fixed 24 fps. For totals beyond the per-model cap, batch multiple clips via sourceImageIndices instead of requesting a single oversized clip."
|
|
539
551
|
},
|
|
540
552
|
"targetResolution": {
|
|
541
553
|
"type": "number",
|
|
@@ -687,7 +699,7 @@
|
|
|
687
699
|
},
|
|
688
700
|
"generateAudio": {
|
|
689
701
|
"type": "boolean",
|
|
690
|
-
"description": "
|
|
702
|
+
"description": "Whether the final video should include generated or retained audio. Omit to include audio by default; set false when the user asks for silent output or no audio. When false, the returned video has no audio track."
|
|
691
703
|
},
|
|
692
704
|
"targetResolution": {
|
|
693
705
|
"type": "number",
|
|
@@ -933,11 +945,11 @@
|
|
|
933
945
|
"ltx23-ia2v",
|
|
934
946
|
"ltx23-a2v"
|
|
935
947
|
],
|
|
936
|
-
"description": "Video model. \"ltx23-ia2v\" (default when image available): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step
|
|
948
|
+
"description": "Video model. \"ltx23-ia2v\" (default when image available): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant. \"ltx23-a2v\" (default when no image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s; this tool supplies the audio plus a required reference image because Seedance text+audio without image/video is unsupported. \"seedance2-mini\": Seedance 2.0 Mini for faster, lower-cost 720p iteration. \"seedance2-fast\": legacy Seedance 2.0 Fast. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster draft/lower-cost Seedance unless the user explicitly says Seedance Fast, pick \"seedance2-fast\" when the user says Seedance Fast / seedance-fast, and pick \"seedance2\" for full/non-fast Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present."
|
|
937
949
|
},
|
|
938
950
|
"generateAudio": {
|
|
939
951
|
"type": "boolean",
|
|
940
|
-
"description": "
|
|
952
|
+
"description": "Whether the final video should include audio. Omit to include audio by default; set false when the user asks for silent output or no audio. When false, the returned video has no audio track; the reference audio is still required and still drives generation."
|
|
941
953
|
},
|
|
942
954
|
"numberOfVariations": {
|
|
943
955
|
"type": "number",
|
|
@@ -23,17 +23,25 @@
|
|
|
23
23
|
"type": "string",
|
|
24
24
|
"enum": [
|
|
25
25
|
"ltx23",
|
|
26
|
-
"wan22"
|
|
26
|
+
"wan22",
|
|
27
|
+
"happyhorse-1.1-i2v",
|
|
28
|
+
"happyhorse-1.1-r2v",
|
|
29
|
+
"minimax-h3-i2v",
|
|
30
|
+
"minimax-h3-flf2v"
|
|
27
31
|
],
|
|
28
|
-
"description": "Which video model to use. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step
|
|
32
|
+
"description": "Which video model to use. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant; 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, or seedance2-fast 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."
|
|
33
|
+
},
|
|
34
|
+
"generateAudio": {
|
|
35
|
+
"type": "boolean",
|
|
36
|
+
"description": "Whether to include generated/native audio for audio-capable models. Omit to include audio by default; set false only when the user explicitly asks for silent output or no audio. When false, the returned video has no audio track. Ignored by audio-less WAN."
|
|
29
37
|
},
|
|
30
38
|
"negativePrompt": {
|
|
31
39
|
"type": "string",
|
|
32
|
-
"description": "
|
|
40
|
+
"description": "Advanced LTX/WAN only. Use this field only when the user explicitly asks to set a separate negative prompt. MiniMax H3 has no negative-prompt input; put requested exclusions in prompt."
|
|
33
41
|
},
|
|
34
42
|
"duration": {
|
|
35
43
|
"type": "number",
|
|
36
|
-
"description": "Video duration in seconds. Default: 5. Use when the user explicitly requests a specific length (e.g., \"make a 10 second video\"). Per-model maximum: ltx23 = 20s, wan22 = 10s (
|
|
44
|
+
"description": "Video duration in seconds. Default: 5. Use when the user explicitly requests a specific length (e.g., \"make a 10 second video\"). Per-model maximum: ltx23 = 20s, wan22 = 10s (clips longer than this are invalid), minimax-h3 = 15.08s with a 5.17s minimum because H3 renders 124-362 frames on a 17-frame grid at a fixed 24 fps. For totals beyond the per-model cap, batch multiple clips via sourceImageIndices instead of requesting a single oversized clip."
|
|
37
45
|
},
|
|
38
46
|
"targetResolution": {
|
|
39
47
|
"type": "number",
|
|
@@ -21,13 +21,13 @@
|
|
|
21
21
|
},
|
|
22
22
|
"duration": {
|
|
23
23
|
"type": "number",
|
|
24
|
-
"description": "Video duration in seconds. Default: 5. Range: 2-20. Use when the user explicitly requests a specific length.",
|
|
24
|
+
"description": "Video duration in seconds. Default: 5. Range: 2-20. Use when the user explicitly requests a specific length. MiniMax H3 is quantized to a 17-frame grid at a fixed 24 fps and renders 124-362 frames, so an H3 clip runs 5.17-15.08 seconds and a requested length outside that window snaps to the nearest valid H3 length.",
|
|
25
25
|
"minimum": 2,
|
|
26
26
|
"maximum": 20
|
|
27
27
|
},
|
|
28
28
|
"negativePrompt": {
|
|
29
29
|
"type": "string",
|
|
30
|
-
"description": "
|
|
30
|
+
"description": "Advanced LTX/WAN only. Use this field only when the user explicitly asks to set a separate negative prompt. MiniMax H3 has no negative-prompt input; put requested exclusions in prompt. Do not set for MiniMax H3, Seedance, or HappyHorse."
|
|
31
31
|
},
|
|
32
32
|
"videoModel": {
|
|
33
33
|
"type": "string",
|
|
@@ -36,13 +36,17 @@
|
|
|
36
36
|
"wan22",
|
|
37
37
|
"seedance2",
|
|
38
38
|
"seedance2-mini",
|
|
39
|
-
"seedance2-fast"
|
|
39
|
+
"seedance2-fast",
|
|
40
|
+
"minimax-h3-t2v",
|
|
41
|
+
"happyhorse-1.1-t2v",
|
|
42
|
+
"happyhorse-1.1-i2v",
|
|
43
|
+
"happyhorse-1.1-r2v"
|
|
40
44
|
],
|
|
41
|
-
"description": "Video model. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step
|
|
45
|
+
"description": "Video model. \"ltx23\" (default): LTX 2.3 with native audio; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant. \"wan22\": Fast 4-step, simple motion, no audio. Default: \"ltx23\". 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 text-to-video uses \"minimax-h3-t2v\". 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. 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: images (up to 9), videos (up to 3), and audios (up to 3), with no more than 12 asset 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."
|
|
42
46
|
},
|
|
43
47
|
"generateAudio": {
|
|
44
48
|
"type": "boolean",
|
|
45
|
-
"description": "
|
|
49
|
+
"description": "Whether to include generated/native audio for audio-capable models. Omit to include audio by default; set false only when the user explicitly asks for silent output or no audio. When false, the returned video has no audio track. Not supported by WAN or HappyHorse."
|
|
46
50
|
},
|
|
47
51
|
"referenceImageIndices": {
|
|
48
52
|
"type": "array",
|
|
@@ -44,11 +44,11 @@
|
|
|
44
44
|
"ltx23-ia2v",
|
|
45
45
|
"ltx23-a2v"
|
|
46
46
|
],
|
|
47
|
-
"description": "Video model. \"ltx23-ia2v\" (default when image available): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step
|
|
47
|
+
"description": "Video model. \"ltx23-ia2v\" (default when image available): LTX 2.3 image+audio to video, audio-reactive with a reference image; Fast/HQ use the distilled 8-step variant and Default Media Quality Pro uses the non-distilled dev variant. \"ltx23-a2v\" (default when no image): LTX 2.3 audio-only to video, no image needed, creates video purely from text prompt + audio with the same quality-tier routing. \"wan-s2v\": WAN 2.2 sound-to-video, best for lip-sync with a face image, fast 4-step. \"seedance2\": full Seedance 2.0 audio-reference video, 4-15s; this tool supplies the audio plus a required reference image because Seedance text+audio without image/video is unsupported. \"seedance2-mini\": Seedance 2.0 Mini for faster, lower-cost 720p iteration. \"seedance2-fast\": legacy Seedance 2.0 Fast. Seedance quality is selected only by this model value: pick \"seedance2-mini\" for faster draft/lower-cost Seedance unless the user explicitly says Seedance Fast, pick \"seedance2-fast\" when the user says Seedance Fast / seedance-fast, and pick \"seedance2\" for full/non-fast Seedance or 1080p/4K. Do not infer the Seedance model from Default Media Quality Fast/HQ/Pro. For Seedance audio-reference prompts, preserve exact spoken dialogue when the user supplied it, and assign @Image1/@Audio1 roles. If the user asks for speech without words, describe the vocal performance without inventing quoted dialogue. Treat lip-sync, voice cloning, and real-human reference behavior as provider-sensitive rather than guaranteed. Omit to auto-select based on whether an image is present."
|
|
48
48
|
},
|
|
49
49
|
"generateAudio": {
|
|
50
50
|
"type": "boolean",
|
|
51
|
-
"description": "
|
|
51
|
+
"description": "Whether the final video should include audio. Omit to include audio by default; set false when the user asks for silent output or no audio. When false, the returned video has no audio track; the reference audio is still required and still drives generation."
|
|
52
52
|
},
|
|
53
53
|
"numberOfVariations": {
|
|
54
54
|
"type": "number",
|
|
@@ -49,7 +49,7 @@
|
|
|
49
49
|
},
|
|
50
50
|
"generateAudio": {
|
|
51
51
|
"type": "boolean",
|
|
52
|
-
"description": "
|
|
52
|
+
"description": "Whether the final video should include generated or retained audio. Omit to include audio by default; set false when the user asks for silent output or no audio. When false, the returned video has no audio track."
|
|
53
53
|
},
|
|
54
54
|
"targetResolution": {
|
|
55
55
|
"type": "number",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"definition.d.ts","sourceRoot":"","sources":["../../../../src/tools/definitions/animate-photo/definition.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAOlD,eAAO,MAAM,UAAU,EAAE,
|
|
1
|
+
{"version":3,"file":"definition.d.ts","sourceRoot":"","sources":["../../../../src/tools/definitions/animate-photo/definition.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAOlD,eAAO,MAAM,UAAU,EAAE,cA0IxB,CAAC"}
|
|
@@ -55,16 +55,20 @@ BATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax to vary
|
|
|
55
55
|
},
|
|
56
56
|
videoModel: {
|
|
57
57
|
type: "string",
|
|
58
|
-
enum: ["ltx23", "wan22"],
|
|
59
|
-
description: 'Which video model to use. "ltx23" (default): LTX 2.3 with native audio
|
|
58
|
+
enum: ["ltx23", "wan22", "minimax-h3-i2v", "minimax-h3-flf2v"],
|
|
59
|
+
description: 'Which video model to use. "ltx23" (default): LTX 2.3 with native audio. "wan22": quick simple motion without audio, up to 10s. "minimax-h3-i2v": MiniMax H3 from one first frame. "minimax-h3-flf2v": MiniMax H3 between required first and last frames; use frameRole="both" and provide the end frame. H3 generates native audio at fixed 24fps for 5.17-15.08s and has no negative-prompt input. Do not set Seedance here; use generate_video with Seedance references.',
|
|
60
60
|
},
|
|
61
61
|
negativePrompt: {
|
|
62
62
|
type: "string",
|
|
63
|
-
description: "Advanced
|
|
63
|
+
description: "Advanced LTX/WAN only. Use this field only when the user explicitly asks to set a separate negative prompt. MiniMax H3 has no negative-prompt input; put requested exclusions in prompt.",
|
|
64
|
+
},
|
|
65
|
+
generateAudio: {
|
|
66
|
+
type: "boolean",
|
|
67
|
+
description: "Whether the returned video should include generated/native audio. Omit to include audio by default; set false only when the user explicitly asks for silent output or no audio. Supported by LTX and MiniMax H3; ignored by audio-less WAN.",
|
|
64
68
|
},
|
|
65
69
|
duration: {
|
|
66
70
|
type: "number",
|
|
67
|
-
description: 'Video duration in seconds. Default: 5.
|
|
71
|
+
description: 'Video duration in seconds. Default: 5. Per-model range: ltx23 = 2-20s, wan22 = 2-10s, MiniMax H3 = 5.17-15.08s snapped to its valid frame grid. For longer totals, batch clips via sourceImageIndices.',
|
|
68
72
|
},
|
|
69
73
|
targetResolution: {
|
|
70
74
|
type: "number",
|
|
@@ -101,7 +105,7 @@ BATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax to vary
|
|
|
101
105
|
frameRole: {
|
|
102
106
|
type: "string",
|
|
103
107
|
enum: ["start", "end", "both"],
|
|
104
|
-
description: 'How to use the source image(s)
|
|
108
|
+
description: 'How to use the source image(s). "start" (default): first frame. "end": last frame. "both": interpolate between first and last frames. For end-frame fan-out, use frameRole="end" with sourceImageIndices. MiniMax H3 i2v supports only "start"; MiniMax H3 flf2v requires "both" plus an end image. For single clips using "both", set sourceImageIndex and endImageIndex; fan-out can use matching sourceImageIndices/endImageIndices.',
|
|
105
109
|
},
|
|
106
110
|
endImageIndex: {
|
|
107
111
|
type: "number",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/animate-photo/definition.ts"],"names":[],"mappings":";;;AAMA,kFAGiD;AACjD,sDAAmE;AAEtD,QAAA,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,eAAe;QACrB,WAAW,EACT,k0OAAk0O;QACp0O,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,oDAA6B;;;;;;;;;;;;;;;;;;;;;;;;;;;;qbA4BsZ;iBAC5a;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,4GAA4G;iBAC/G;gBACD,oBAAoB,EAAE;oBACpB,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,uEAAgD;iBAC9D;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC;
|
|
1
|
+
{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/animate-photo/definition.ts"],"names":[],"mappings":";;;AAMA,kFAGiD;AACjD,sDAAmE;AAEtD,QAAA,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,eAAe;QACrB,WAAW,EACT,k0OAAk0O;QACp0O,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,oDAA6B;;;;;;;;;;;;;;;;;;;;;;;;;;;;qbA4BsZ;iBAC5a;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,4GAA4G;iBAC/G;gBACD,oBAAoB,EAAE;oBACpB,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,uEAAgD;iBAC9D;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,gBAAgB,EAAE,kBAAkB,CAAC;oBAC9D,WAAW,EACT,4cAA4c;iBAC/c;gBACD,cAAc,EAAE;oBACd,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,0LAA0L;iBAC7L;gBACD,aAAa,EAAE;oBACb,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,6OAA6O;iBAChP;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,wMAAwM;iBAC3M;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,sZAAsZ;iBACzZ;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,8bAA8b;iBACjc;gBACD,kBAAkB,EAAE;oBAClB,IAAI,EAAE,OAAO;oBACb,KAAK,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE;oBACzB,QAAQ,EAAE,CAAC;oBACX,QAAQ,EAAE,EAAE;oBACZ,WAAW,EACT,qqGAAqqG;iBACxqG;gBACD,OAAO,EAAE;oBACP,IAAI,EAAE,OAAO;oBACb,KAAK,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE;oBACzB,QAAQ,EAAE,CAAC;oBACX,QAAQ,EAAE,EAAE;oBACZ,WAAW,EACT,2hEAA2hE;iBAC9hE;gBACD,kBAAkB,EAAE;oBAClB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,2XAA2X;oBAC7X,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE,mCAAwB;iBACtC;gBACD,SAAS,EAAE;oBACT,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,OAAO,EAAE,KAAK,EAAE,MAAM,CAAC;oBAC9B,WAAW,EACT,yaAAya;iBAC5a;gBACD,aAAa,EAAE;oBACb,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,ykBAAykB;iBAC5kB;gBACD,eAAe,EAAE;oBACf,IAAI,EAAE,OAAO;oBACb,KAAK,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE;oBACzB,QAAQ,EAAE,CAAC;oBACX,QAAQ,EAAE,EAAE;oBACZ,WAAW,EACT,whCAAwhC;iBAC3hC;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,mjBAAmjB;iBACtjB;aACF;YACD,QAAQ,EAAE,CAAC,QAAQ,CAAC;SACrB;KACF;CACF,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"definition.d.ts","sourceRoot":"","sources":["../../../../src/tools/definitions/generate-video/definition.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAUlD,eAAO,MAAM,UAAU,EAAE,
|
|
1
|
+
{"version":3,"file":"definition.d.ts","sourceRoot":"","sources":["../../../../src/tools/definitions/generate-video/definition.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,aAAa,CAAC;AAUlD,eAAO,MAAM,UAAU,EAAE,cA4IxB,CAAC"}
|
|
@@ -61,7 +61,7 @@ BATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax. This i
|
|
|
61
61
|
},
|
|
62
62
|
negativePrompt: {
|
|
63
63
|
type: "string",
|
|
64
|
-
description: "Advanced
|
|
64
|
+
description: "Advanced LTX/WAN only. Use this field only when the user explicitly asks to set a separate negative prompt. MiniMax H3 has no negative-prompt input; put requested exclusions in prompt. Do not set for MiniMax H3, Seedance, or HappyHorse.",
|
|
65
65
|
},
|
|
66
66
|
videoModel: {
|
|
67
67
|
type: "string",
|
|
@@ -71,18 +71,19 @@ BATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax. This i
|
|
|
71
71
|
"seedance2",
|
|
72
72
|
"seedance2-mini",
|
|
73
73
|
"seedance2-fast",
|
|
74
|
+
"minimax-h3-t2v",
|
|
74
75
|
"happyhorse-1.1-t2v",
|
|
75
76
|
"happyhorse-1.1-i2v",
|
|
76
77
|
"happyhorse-1.1-r2v",
|
|
77
78
|
],
|
|
78
|
-
description: 'Video model. "ltx23" (default): LTX 2.3 with native audio
|
|
79
|
+
description: 'Video model. "ltx23" (default): LTX 2.3 with native audio. "wan22": quick simple motion without audio. "minimax-h3-t2v": MiniMax H3 text-to-video with native audio, fixed 24fps, 5.17-15.08s, and a 768p-class 32px-grid canvas; use animate_photo for H3 image-conditioned modes. Seedance quality is selected only by model: use "seedance2-mini" for Seedance 2.0 Mini or faster/lower-cost 720p iteration, use "seedance2-fast" only when the user explicitly 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. ' +
|
|
79
80
|
toolPromptMarkers_js_1.SEEDANCE_TOOL_MULTIMODAL_REFERENCE_GUIDANCE +
|
|
80
81
|
' ' +
|
|
81
82
|
toolPromptMarkers_js_1.HAPPYHORSE_GENERATE_VIDEO_MODEL_DESCRIPTION,
|
|
82
83
|
},
|
|
83
84
|
generateAudio: {
|
|
84
85
|
type: "boolean",
|
|
85
|
-
description: "
|
|
86
|
+
description: "Whether the returned video should include generated/native audio. Omit to include audio by default; set false only when the user explicitly asks for silent output or no audio. Supported by LTX, MiniMax H3, and Seedance; not supported by WAN or HappyHorse.",
|
|
86
87
|
},
|
|
87
88
|
referenceImageIndices: {
|
|
88
89
|
type: "array",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/generate-video/definition.ts"],"names":[],"mappings":";;;AAMA,kFAMiD;AACjD,sDAAmE;AAEtD,QAAA,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,gBAAgB;QACtB,WAAW,EACT,g5IAAg5I;QACl5I,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,oDAA6B;;;;;;;;;;;;;;;;;;;;;;;;;;;;kcA4Bma;iBACzb;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,yDAAkC;iBAChD;gBACD,oBAAoB,EAAE;oBACpB,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,wEAAiD;iBAC/D;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,8GAA8G;oBAChH,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,cAAc,EAAE;oBACd,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,
|
|
1
|
+
{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/generate-video/definition.ts"],"names":[],"mappings":";;;AAMA,kFAMiD;AACjD,sDAAmE;AAEtD,QAAA,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,gBAAgB;QACtB,WAAW,EACT,g5IAAg5I;QACl5I,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,oDAA6B;;;;;;;;;;;;;;;;;;;;;;;;;;;;kcA4Bma;iBACzb;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,yDAAkC;iBAChD;gBACD,oBAAoB,EAAE;oBACpB,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,wEAAiD;iBAC/D;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,8GAA8G;oBAChH,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,cAAc,EAAE;oBACd,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,8OAA8O;iBACjP;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE;wBACJ,OAAO;wBACP,OAAO;wBACP,WAAW;wBACX,gBAAgB;wBAChB,gBAAgB;wBAChB,gBAAgB;wBAChB,oBAAoB;wBACpB,oBAAoB;wBACpB,oBAAoB;qBACrB;oBACD,WAAW,EACT,4yBAA4yB;wBAC5yB,kEAA2C;wBAC3C,GAAG;wBACH,kEAA2C;iBAC9C;gBACD,aAAa,EAAE;oBACb,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,iQAAiQ;iBACpQ;gBACD,qBAAqB,EAAE;oBACrB,IAAI,EAAE,OAAO;oBACb,KAAK,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE;oBACzB,WAAW,EACT,w0BAAw0B;iBAC30B;gBACD,qBAAqB,EAAE;oBACrB,IAAI,EAAE,OAAO;oBACb,KAAK,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE;oBACzB,WAAW,EACT,mfAAmf;iBACtf;gBACD,qBAAqB,EAAE;oBACrB,IAAI,EAAE,OAAO;oBACb,KAAK,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE;oBACzB,WAAW,EACT,yvBAAyvB;iBAC5vB;gBACD,KAAK,EAAE;oBACL,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,i/BAAi/B;iBACp/B;gBACD,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,urBAAurB;iBAC1rB;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,o1BAAo1B;iBACv1B;gBACD,kBAAkB,EAAE;oBAClB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,4XAA4X;oBAC9X,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE,mCAAwB;iBACtC;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,8jBAA8jB;iBACjkB;aACF;YACD,QAAQ,EAAE,CAAC,QAAQ,CAAC;SACrB;KACF;CACF,CAAC"}
|
|
@@ -69,7 +69,7 @@ BATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax to vary
|
|
|
69
69
|
},
|
|
70
70
|
generateAudio: {
|
|
71
71
|
type: "boolean",
|
|
72
|
-
description: "
|
|
72
|
+
description: "Whether the returned video should include audio. Omit to include audio by default; set false when the user asks for silent output or no audio. The reference audio is still required and still drives generation even when the returned video has no audio track.",
|
|
73
73
|
},
|
|
74
74
|
numberOfVariations: {
|
|
75
75
|
type: "number",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/sound-to-video/definition.ts"],"names":[],"mappings":";;;AAMA,kFAIiD;AACjD,sDAAmE;AAEtD,QAAA,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,gBAAgB;QACtB,WAAW,EACT,qoDAAqoD;QACvoD,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,uDAAgC;;;;;;;;;;;;;;;;;;;;kdAoBgb;iBACzc;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,yDAAkC;iBAChD;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,yPAAyP;iBAC5P;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,0OAA0O;iBAC7O;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,+OAA+O;oBACjP,OAAO,EAAE,CAAC;iBACX;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,qNAAqN;oBACvN,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,SAAS,EAAE,WAAW,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,YAAY,EAAE,WAAW,CAAC;oBAC7F,WAAW,EACT,8/BAA8/B;wBAC9/B,6DAAsC;wBACtC,4DAA4D;iBAC/D;gBACD,aAAa,EAAE;oBACb,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,
|
|
1
|
+
{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/sound-to-video/definition.ts"],"names":[],"mappings":";;;AAMA,kFAIiD;AACjD,sDAAmE;AAEtD,QAAA,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,gBAAgB;QACtB,WAAW,EACT,qoDAAqoD;QACvoD,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,uDAAgC;;;;;;;;;;;;;;;;;;;;kdAoBgb;iBACzc;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,yDAAkC;iBAChD;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,yPAAyP;iBAC5P;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,0OAA0O;iBAC7O;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,+OAA+O;oBACjP,OAAO,EAAE,CAAC;iBACX;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,qNAAqN;oBACvN,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,SAAS,EAAE,WAAW,EAAE,gBAAgB,EAAE,gBAAgB,EAAE,YAAY,EAAE,WAAW,CAAC;oBAC7F,WAAW,EACT,8/BAA8/B;wBAC9/B,6DAAsC;wBACtC,4DAA4D;iBAC/D;gBACD,aAAa,EAAE;oBACb,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,mQAAmQ;iBACtQ;gBACD,kBAAkB,EAAE;oBAClB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,iSAAiS;oBACnS,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,6YAA6Y;iBAChZ;gBACD,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE,mCAAwB;iBACtC;aACF;YACD,QAAQ,EAAE,CAAC,QAAQ,CAAC;SACrB;KACF;CACF,CAAC"}
|
|
@@ -79,7 +79,7 @@ BATCH VARIATIONS: When numberOfVariations > 1, use Dynamic Prompt syntax to vary
|
|
|
79
79
|
},
|
|
80
80
|
generateAudio: {
|
|
81
81
|
type: "boolean",
|
|
82
|
-
description:
|
|
82
|
+
description: "Whether the returned video should include generated or retained audio. Omit to include audio by default; set false when the user asks for silent output or no audio.",
|
|
83
83
|
},
|
|
84
84
|
targetResolution: {
|
|
85
85
|
type: "number",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/video-to-video/definition.ts"],"names":[],"mappings":";;;AAMA,kFAIiD;AAEpC,QAAA,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,gBAAgB;QACtB,WAAW,EACT,4vBAA4vB;QAC9vB,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,uDAAgC;;;;;;;;;;;;;;;;;;;uRAmBqP;iBAC9Q;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,yDAAkC;iBAChD;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,qYAAqY;iBACxY;gBACD,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE;wBACJ,cAAc;wBACd,iBAAiB;wBACjB,OAAO;wBACP,MAAM;wBACN,OAAO;wBACP,UAAU;wBACV,UAAU;wBACV,SAAS;wBACT,cAAc;qBACf;oBACD,WAAW,EACT,sFAAsF;wBACtF,kMAAkM;wBAClM,sNAAsN;wBACtN,mSAAmS;wBACnS,mQAAmQ;wBACnQ,iRAAiR;wBACjR,yXAAyX;wBACzX,sbAAsb;wBACtb,4cAA4c;wBAC5c,+RAA+R,2DAAoC,yHAAyH;wBAC5b,2QAA2Q;iBAC9Q;gBACD,cAAc,EAAE;oBACd,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,4XAA4X;iBAC/X;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,WAAW,EAAE,eAAe,EAAE,WAAW,EAAE,gBAAgB,EAAE,gBAAgB,CAAC;oBACrF,WAAW,EACT,ogBAAogB;iBACvgB;gBACD,aAAa,EAAE;oBACb,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,
|
|
1
|
+
{"version":3,"file":"definition.js","sourceRoot":"","sources":["../../../../src/tools/definitions/video-to-video/definition.ts"],"names":[],"mappings":";;;AAMA,kFAIiD;AAEpC,QAAA,UAAU,GAAmB;IACxC,IAAI,EAAE,UAAU;IAChB,QAAQ,EAAE;QACR,IAAI,EAAE,gBAAgB;QACtB,WAAW,EACT,4vBAA4vB;QAC9vB,UAAU,EAAE;YACV,IAAI,EAAE,QAAQ;YACd,UAAU,EAAE;gBACV,MAAM,EAAE;oBACN,IAAI,EAAE,QAAQ;oBACd,WAAW,EAAE;;EAErB,uDAAgC;;;;;;;;;;;;;;;;;;;uRAmBqP;iBAC9Q;gBACD,YAAY,EAAE;oBACZ,IAAI,EAAE,SAAS;oBACf,WAAW,EAAE,yDAAkC;iBAChD;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,qYAAqY;iBACxY;gBACD,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE;wBACJ,cAAc;wBACd,iBAAiB;wBACjB,OAAO;wBACP,MAAM;wBACN,OAAO;wBACP,UAAU;wBACV,UAAU;wBACV,SAAS;wBACT,cAAc;qBACf;oBACD,WAAW,EACT,sFAAsF;wBACtF,kMAAkM;wBAClM,sNAAsN;wBACtN,mSAAmS;wBACnS,mQAAmQ;wBACnQ,iRAAiR;wBACjR,yXAAyX;wBACzX,sbAAsb;wBACtb,4cAA4c;wBAC5c,+RAA+R,2DAAoC,yHAAyH;wBAC5b,2QAA2Q;iBAC9Q;gBACD,cAAc,EAAE;oBACd,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,4XAA4X;iBAC/X;gBACD,UAAU,EAAE;oBACV,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,WAAW,EAAE,eAAe,EAAE,WAAW,EAAE,gBAAgB,EAAE,gBAAgB,CAAC;oBACrF,WAAW,EACT,ogBAAogB;iBACvgB;gBACD,aAAa,EAAE;oBACb,IAAI,EAAE,SAAS;oBACf,WAAW,EACT,sKAAsK;iBACzK;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,iTAAiT;iBACpT;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,8NAA8N;iBACjO;gBACD,gBAAgB,EAAE;oBAChB,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,QAAQ,EAAE,KAAK,EAAE,QAAQ,EAAE,MAAM,EAAE,OAAO,CAAC;oBAClD,WAAW,EACT,2cAA2c;iBAC9c;gBACD,mBAAmB,EAAE;oBACnB,IAAI,EAAE,QAAQ;oBACd,IAAI,EAAE,CAAC,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,MAAM,CAAC;oBACnD,WAAW,EACT,4VAA4V;iBAC/V;gBACD,cAAc,EAAE;oBACd,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,4SAA4S;iBAC/S;gBACD,QAAQ,EAAE;oBACR,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,wgBAAwgB;oBAC1gB,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;gBACD,kBAAkB,EAAE;oBAClB,IAAI,EAAE,QAAQ;oBACd,WAAW,EACT,4DAA4D;oBAC9D,OAAO,EAAE,CAAC;oBACV,OAAO,EAAE,EAAE;iBACZ;aACF;YACD,QAAQ,EAAE,CAAC,QAAQ,CAAC;SACrB;KACF;CACF,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"modelRegistry.d.ts","sourceRoot":"","sources":["../../../src/tools/shared/modelRegistry.ts"],"names":[],"mappings":"AASA,MAAM,WAAW,WAAW;IAC1B,GAAG,EAAE,MAAM,CAAC;IACZ,WAAW,EAAE,MAAM,CAAC;CACrB;AAqBD,eAAO,MAAM,cAAc,EAAE,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,
|
|
1
|
+
{"version":3,"file":"modelRegistry.d.ts","sourceRoot":"","sources":["../../../src/tools/shared/modelRegistry.ts"],"names":[],"mappings":"AASA,MAAM,WAAW,WAAW;IAC1B,GAAG,EAAE,MAAM,CAAC;IACZ,WAAW,EAAE,MAAM,CAAC;CACrB;AAqBD,eAAO,MAAM,cAAc,EAAE,MAAM,CAAC,MAAM,EAAE,WAAW,EAAE,CAuExD,CAAC;AAkBF,wBAAgB,cAAc,CAAC,QAAQ,EAAE,MAAM,GAAG,MAAM,CAGvD;AAGD,wBAAgB,iBAAiB,CAAC,QAAQ,EAAE,MAAM,GAAG,OAAO,CAE3D;AAGD,wBAAgB,eAAe,CAAC,QAAQ,EAAE,MAAM,GAAG,WAAW,EAAE,CAE/D;AAGD,wBAAgB,oBAAoB,CAClC,QAAQ,EAAE,MAAM,EAChB,eAAe,CAAC,EAAE,MAAM,GACvB,WAAW,EAAE,CAIf"}
|
|
@@ -62,6 +62,7 @@ exports.MODELS_BY_TOOL = {
|
|
|
62
62
|
{ key: 'seedance2', displayName: 'Seedance 2.0' },
|
|
63
63
|
{ key: 'seedance2-mini', displayName: 'Seedance 2.0 Mini' },
|
|
64
64
|
{ key: 'seedance2-fast', displayName: 'Seedance 2.0 Fast' },
|
|
65
|
+
{ key: 'minimax-h3-t2v', displayName: 'MiniMax H3 (Text to Video)' },
|
|
65
66
|
{ key: 'happyhorse-1.1-t2v', displayName: 'HappyHorse 1.1 (Text to Video)' },
|
|
66
67
|
{ key: 'happyhorse-1.1-i2v', displayName: 'HappyHorse 1.1 (Image to Video)' },
|
|
67
68
|
{ key: 'happyhorse-1.1-r2v', displayName: 'HappyHorse 1.1 (Reference to Video)' },
|
|
@@ -69,6 +70,8 @@ exports.MODELS_BY_TOOL = {
|
|
|
69
70
|
animate_photo: [
|
|
70
71
|
{ key: 'ltx23', displayName: 'LTX 2.3 22B' },
|
|
71
72
|
{ key: 'wan22', displayName: 'WAN 2.2 14B' },
|
|
73
|
+
{ key: 'minimax-h3-i2v', displayName: 'MiniMax H3 (Image to Video)' },
|
|
74
|
+
{ key: 'minimax-h3-flf2v', displayName: 'MiniMax H3 (First + Last Frame)' },
|
|
72
75
|
],
|
|
73
76
|
sound_to_video: [
|
|
74
77
|
{ key: 'wan-s2v', displayName: 'WAN 2.2 S2V' },
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"modelRegistry.js","sourceRoot":"","sources":["../../../src/tools/shared/modelRegistry.ts"],"names":[],"mappings":";;;
|
|
1
|
+
{"version":3,"file":"modelRegistry.js","sourceRoot":"","sources":["../../../src/tools/shared/modelRegistry.ts"],"names":[],"mappings":";;;AA0HA,wCAGC;AAGD,8CAEC;AAGD,0CAEC;AAGD,oDAOC;AAhID,MAAM,mBAAmB,GAAkB;IACzC,EAAE,GAAG,EAAE,MAAM,EAAE,WAAW,EAAE,gCAAgC,EAAE;IAC9D,EAAE,GAAG,EAAE,IAAI,EAAE,WAAW,EAAE,sBAAsB,EAAE;IAClD,EAAE,GAAG,EAAE,KAAK,EAAE,WAAW,EAAE,kBAAkB,EAAE;CAChD,CAAC;AAGF,MAAM,mBAAmB,GAAkB;IACzC,EAAE,GAAG,EAAE,MAAM,EAAE,WAAW,EAAE,gCAAgC,EAAE;IAC9D,EAAE,GAAG,EAAE,IAAI,EAAE,WAAW,EAAE,sBAAsB,EAAE;CACnD,CAAC;AAMW,QAAA,cAAc,GAAkC;IAC3D,cAAc,EAAE;QACd,EAAE,GAAG,EAAE,aAAa,EAAE,WAAW,EAAE,aAAa,EAAE;QAClD,EAAE,GAAG,EAAE,SAAS,EAAE,WAAW,EAAE,eAAe,EAAE;QAChD,EAAE,GAAG,EAAE,SAAS,EAAE,WAAW,EAAE,SAAS,EAAE;QAC1C,EAAE,GAAG,EAAE,cAAc,EAAE,WAAW,EAAE,cAAc,EAAE;QACpD,EAAE,GAAG,EAAE,kBAAkB,EAAE,WAAW,EAAE,mBAAmB,EAAE;QAC7D,EAAE,GAAG,EAAE,oBAAoB,EAAE,WAAW,EAAE,0BAA0B,EAAE;QACtE,EAAE,GAAG,EAAE,kBAAkB,EAAE,WAAW,EAAE,mBAAmB,EAAE;QAC7D,EAAE,GAAG,EAAE,YAAY,EAAE,WAAW,EAAE,aAAa,EAAE;QACjD,EAAE,GAAG,EAAE,eAAe,EAAE,WAAW,EAAE,eAAe,EAAE;QACtD,EAAE,GAAG,EAAE,YAAY,EAAE,WAAW,EAAE,aAAa,EAAE;QACjD,EAAE,GAAG,EAAE,OAAO,EAAE,WAAW,EAAE,YAAY,EAAE;QAC3C,EAAE,GAAG,EAAE,SAAS,EAAE,WAAW,EAAE,wBAAwB,EAAE;QACzD,EAAE,GAAG,EAAE,WAAW,EAAE,WAAW,EAAE,iBAAiB,EAAE;QACpD,EAAE,GAAG,EAAE,qBAAqB,EAAE,WAAW,EAAE,2BAA2B,EAAE;QACxE,EAAE,GAAG,EAAE,WAAW,EAAE,WAAW,EAAE,0BAA0B,EAAE;QAC7D,EAAE,GAAG,EAAE,cAAc,EAAE,WAAW,EAAE,kBAAkB,EAAE;QACxD,EAAE,GAAG,EAAE,mBAAmB,EAAE,WAAW,EAAE,oBAAoB,EAAE;QAC/D,EAAE,GAAG,EAAE,iBAAiB,EAAE,WAAW,EAAE,oBAAoB,EAAE;QAC7D,EAAE,GAAG,EAAE,iBAAiB,EAAE,WAAW,EAAE,oBAAoB,EAAE;QAC7D,EAAE,GAAG,EAAE,eAAe,EAAE,WAAW,EAAE,2BAA2B,EAAE;QAClE,EAAE,GAAG,EAAE,mBAAmB,EAAE,WAAW,EAAE,wBAAwB,EAAE;QACnE,EAAE,GAAG,EAAE,mBAAmB,EAAE,WAAW,EAAE,sBAAsB,EAAE;QACjE,EAAE,GAAG,EAAE,eAAe,EAAE,WAAW,EAAE,uBAAuB,EAAE;QAC9D,EAAE,GAAG,EAAE,cAAc,EAAE,WAAW,EAAE,0BAA0B,EAAE;QAChE,EAAE,GAAG,EAAE,eAAe,EAAE,WAAW,EAAE,iBAAiB,EAAE;QACxD,EAAE,GAAG,EAAE,gBAAgB,EAAE,WAAW,EAAE,qBAAqB,EAAE;QAC7D,EAAE,GAAG,EAAE,gBAAgB,EAAE,WAAW,EAAE,gBAAgB,EAAE;KACzD;IACD,UAAU,EAAE;QACV,EAAE,GAAG,EAAE,aAAa,EAAE,WAAW,EAAE,aAAa,EAAE;QAClD,EAAE,GAAG,EAAE,gBAAgB,EAAE,WAAW,EAAE,2BAA2B,EAAE;QACnE,EAAE,GAAG,EAAE,MAAM,EAAE,WAAW,EAAE,sBAAsB,EAAE;QACpD,EAAE,GAAG,EAAE,OAAO,EAAE,WAAW,EAAE,YAAY,EAAE;QAC3C,EAAE,GAAG,EAAE,oBAAoB,EAAE,WAAW,EAAE,gCAAgC,EAAE;QAC5E,EAAE,GAAG,EAAE,gCAAgC,EAAE,WAAW,EAAE,iCAAiC,EAAE;KAC1F;IACD,aAAa,EAAE,mBAAmB;IAClC,WAAW,EAAE,mBAAmB;IAChC,aAAa,EAAE,mBAAmB;IAClC,YAAY,EAAE,mBAAmB;IACjC,cAAc,EAAE;QACd,EAAE,GAAG,EAAE,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE;QAC5C,EAAE,GAAG,EAAE,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE;QAC5C,EAAE,GAAG,EAAE,WAAW,EAAE,WAAW,EAAE,cAAc,EAAE;QACjD,EAAE,GAAG,EAAE,gBAAgB,EAAE,WAAW,EAAE,mBAAmB,EAAE;QAC3D,EAAE,GAAG,EAAE,gBAAgB,EAAE,WAAW,EAAE,mBAAmB,EAAE;QAC3D,EAAE,GAAG,EAAE,gBAAgB,EAAE,WAAW,EAAE,4BAA4B,EAAE;QACpE,EAAE,GAAG,EAAE,oBAAoB,EAAE,WAAW,EAAE,gCAAgC,EAAE;QAC5E,EAAE,GAAG,EAAE,oBAAoB,EAAE,WAAW,EAAE,iCAAiC,EAAE;QAC7E,EAAE,GAAG,EAAE,oBAAoB,EAAE,WAAW,EAAE,qCAAqC,EAAE;KAClF;IACD,aAAa,EAAE;QACb,EAAE,GAAG,EAAE,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE;QAC5C,EAAE,GAAG,EAAE,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE;QAC5C,EAAE,GAAG,EAAE,gBAAgB,EAAE,WAAW,EAAE,6BAA6B,EAAE;QACrE,EAAE,GAAG,EAAE,kBAAkB,EAAE,WAAW,EAAE,iCAAiC,EAAE;KAC5E;IACD,cAAc,EAAE;QACd,EAAE,GAAG,EAAE,SAAS,EAAE,WAAW,EAAE,aAAa,EAAE;QAC9C,EAAE,GAAG,EAAE,WAAW,EAAE,WAAW,EAAE,0BAA0B,EAAE;QAC7D,EAAE,GAAG,EAAE,gBAAgB,EAAE,WAAW,EAAE,+BAA+B,EAAE;QACvE,EAAE,GAAG,EAAE,gBAAgB,EAAE,WAAW,EAAE,+BAA+B,EAAE;QACvE,EAAE,GAAG,EAAE,YAAY,EAAE,WAAW,EAAE,qBAAqB,EAAE;QACzD,EAAE,GAAG,EAAE,WAAW,EAAE,WAAW,EAAE,oBAAoB,EAAE;KACxD;IACD,cAAc,EAAE;QACd,EAAE,GAAG,EAAE,OAAO,EAAE,WAAW,EAAE,oBAAoB,EAAE;QACnD,EAAE,GAAG,EAAE,KAAK,EAAE,WAAW,EAAE,kBAAkB,EAAE;KAChD;CACF,CAAC;AAGF,MAAM,iBAAiB,GAAG;IACxB,eAAe;IACf,aAAa;IACb,eAAe;IACf,cAAc;CACf,CAAC;AAEF,MAAM,qBAAqB,GAAG,CAAC,gBAAgB,EAAE,eAAe,EAAE,gBAAgB,CAAC,CAAC;AAQpF,SAAgB,cAAc,CAAC,QAAgB;IAC7C,IAAI,iBAAiB,CAAC,QAAQ,CAAC,QAAQ,CAAC;QAAE,OAAO,SAAS,CAAC;IAC3D,OAAO,qBAAqB,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,OAAO,CAAC;AAC3E,CAAC;AAGD,SAAgB,iBAAiB,CAAC,QAAgB;IAChD,OAAO,iBAAiB,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC;AAC9C,CAAC;AAGD,SAAgB,eAAe,CAAC,QAAgB;IAC9C,OAAO,sBAAc,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC;AACxC,CAAC;AAGD,SAAgB,oBAAoB,CAClC,QAAgB,EAChB,eAAwB;IAExB,MAAM,GAAG,GAAG,eAAe,CAAC,QAAQ,CAAC,CAAC;IACtC,IAAI,CAAC,eAAe;QAAE,OAAO,GAAG,CAAC;IACjC,OAAO,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,GAAG,KAAK,eAAe,CAAC,CAAC;AACtD,CAAC"}
|
|
@@ -52,6 +52,66 @@ export const VIDEO_MODEL_CONFIGS = {
|
|
|
52
52
|
resolutionTiers: [1088, 768],
|
|
53
53
|
resolutionThreshold: 720,
|
|
54
54
|
},
|
|
55
|
+
"minimax-h3-t2v": {
|
|
56
|
+
model: "minimax-h3-fl2va-fp8_t2v",
|
|
57
|
+
fps: 24,
|
|
58
|
+
steps: 20,
|
|
59
|
+
guidance: 1,
|
|
60
|
+
dimensionDivisor: 32,
|
|
61
|
+
minDimension: 32,
|
|
62
|
+
maxDimension: 1344,
|
|
63
|
+
sampler: "res_multistep",
|
|
64
|
+
scheduler: "simple",
|
|
65
|
+
resolutionTiers: [768],
|
|
66
|
+
frameBase: 124,
|
|
67
|
+
frameStep: 17,
|
|
68
|
+
minFrames: 124,
|
|
69
|
+
maxFrames: 362,
|
|
70
|
+
maxPixels: 1032192,
|
|
71
|
+
nativeAudio: true,
|
|
72
|
+
supportsAudioToggle: true,
|
|
73
|
+
supportsNegativePrompt: false,
|
|
74
|
+
},
|
|
75
|
+
"minimax-h3-i2v": {
|
|
76
|
+
model: "minimax-h3-fl2va-fp8_i2v",
|
|
77
|
+
fps: 24,
|
|
78
|
+
steps: 20,
|
|
79
|
+
guidance: 1,
|
|
80
|
+
dimensionDivisor: 32,
|
|
81
|
+
minDimension: 32,
|
|
82
|
+
maxDimension: 1344,
|
|
83
|
+
sampler: "res_multistep",
|
|
84
|
+
scheduler: "simple",
|
|
85
|
+
resolutionTiers: [768],
|
|
86
|
+
frameBase: 124,
|
|
87
|
+
frameStep: 17,
|
|
88
|
+
minFrames: 124,
|
|
89
|
+
maxFrames: 362,
|
|
90
|
+
maxPixels: 1032192,
|
|
91
|
+
nativeAudio: true,
|
|
92
|
+
supportsAudioToggle: true,
|
|
93
|
+
supportsNegativePrompt: false,
|
|
94
|
+
},
|
|
95
|
+
"minimax-h3-flf2v": {
|
|
96
|
+
model: "minimax-h3-fl2va-fp8_flf2v",
|
|
97
|
+
fps: 24,
|
|
98
|
+
steps: 20,
|
|
99
|
+
guidance: 1,
|
|
100
|
+
dimensionDivisor: 32,
|
|
101
|
+
minDimension: 32,
|
|
102
|
+
maxDimension: 1344,
|
|
103
|
+
sampler: "res_multistep",
|
|
104
|
+
scheduler: "simple",
|
|
105
|
+
resolutionTiers: [768],
|
|
106
|
+
frameBase: 124,
|
|
107
|
+
frameStep: 17,
|
|
108
|
+
minFrames: 124,
|
|
109
|
+
maxFrames: 362,
|
|
110
|
+
maxPixels: 1032192,
|
|
111
|
+
nativeAudio: true,
|
|
112
|
+
supportsAudioToggle: true,
|
|
113
|
+
supportsNegativePrompt: false,
|
|
114
|
+
},
|
|
55
115
|
seedance2: {
|
|
56
116
|
model: "seedance-2-0",
|
|
57
117
|
fps: 24,
|
|
@@ -225,16 +285,19 @@ export function calculateVideoDimensions(imageWidth, imageHeight, targetResoluti
|
|
|
225
285
|
effectiveW = Math.sqrt(srcArea * ratio);
|
|
226
286
|
effectiveH = srcArea / effectiveW;
|
|
227
287
|
}
|
|
288
|
+
const roundedTarget = targetResolution === undefined
|
|
289
|
+
? undefined
|
|
290
|
+
: Math.round(targetResolution / divisor) * divisor;
|
|
228
291
|
if (parsed?.type !== "exact" &&
|
|
229
292
|
config.resolutionTiers &&
|
|
230
293
|
config.resolutionTiers.length > 0 &&
|
|
231
|
-
|
|
294
|
+
(roundedTarget === undefined || config.resolutionTiers.includes(roundedTarget))) {
|
|
232
295
|
const srcShorter = Math.min(effectiveW, effectiveH);
|
|
233
296
|
const threshold = config.resolutionThreshold ??
|
|
234
297
|
config.resolutionTiers[config.resolutionTiers.length - 1];
|
|
235
|
-
const tier = srcShorter < threshold
|
|
298
|
+
const tier = roundedTarget ?? (srcShorter < threshold
|
|
236
299
|
? config.resolutionTiers[config.resolutionTiers.length - 1]
|
|
237
|
-
: config.resolutionTiers[0];
|
|
300
|
+
: config.resolutionTiers[0]);
|
|
238
301
|
let w, h;
|
|
239
302
|
if (effectiveW <= effectiveH) {
|
|
240
303
|
w = tier;
|
|
@@ -246,7 +309,7 @@ export function calculateVideoDimensions(imageWidth, imageHeight, targetResoluti
|
|
|
246
309
|
}
|
|
247
310
|
w = Math.min(maxDim, w);
|
|
248
311
|
h = Math.min(maxDim, h);
|
|
249
|
-
return
|
|
312
|
+
return constrainVideoDimensions(w, h, config);
|
|
250
313
|
}
|
|
251
314
|
let w = effectiveW;
|
|
252
315
|
let h = effectiveH;
|
|
@@ -277,12 +340,35 @@ export function calculateVideoDimensions(imageWidth, imageHeight, targetResoluti
|
|
|
277
340
|
h = Math.round(h / divisor) * divisor;
|
|
278
341
|
w = Math.max(minDim, Math.min(maxDim, w));
|
|
279
342
|
h = Math.max(minDim, Math.min(maxDim, h));
|
|
343
|
+
return constrainVideoDimensions(w, h, config);
|
|
344
|
+
}
|
|
345
|
+
function constrainVideoDimensions(width, height, config) {
|
|
346
|
+
const divisor = config.dimensionDivisor;
|
|
347
|
+
const minDim = config.minDimension;
|
|
348
|
+
const maxDim = config.maxDimension;
|
|
349
|
+
let w = Math.max(minDim, Math.min(maxDim, Math.round(width / divisor) * divisor));
|
|
350
|
+
let h = Math.max(minDim, Math.min(maxDim, Math.round(height / divisor) * divisor));
|
|
351
|
+
if (config.maxPixels && w * h > config.maxPixels) {
|
|
352
|
+
const scale = Math.sqrt(config.maxPixels / (w * h));
|
|
353
|
+
w = Math.max(minDim, Math.floor((w * scale) / divisor) * divisor);
|
|
354
|
+
h = Math.max(minDim, Math.floor((h * scale) / divisor) * divisor);
|
|
355
|
+
while (w * h > config.maxPixels && (w > minDim || h > minDim)) {
|
|
356
|
+
if ((h >= w && h > minDim) || w <= minDim)
|
|
357
|
+
h -= divisor;
|
|
358
|
+
else
|
|
359
|
+
w -= divisor;
|
|
360
|
+
}
|
|
361
|
+
}
|
|
280
362
|
return { width: w, height: h };
|
|
281
363
|
}
|
|
282
364
|
export function calculateVideoFrames(duration = 5, modelId = DEFAULT_VIDEO_MODEL, qualityTier = "fast") {
|
|
283
365
|
const config = getVideoModelConfig(modelId, qualityTier);
|
|
284
366
|
const generationFps = config.internalFps ?? config.fps;
|
|
285
|
-
const
|
|
286
|
-
|
|
367
|
+
const frameBase = config.frameBase ?? 1;
|
|
368
|
+
const frameStep = config.frameStep ?? 8;
|
|
369
|
+
const rawFrames = generationFps * duration + (frameBase === 1 ? 1 : 0);
|
|
370
|
+
const snapped = frameBase + Math.round((rawFrames - frameBase) / frameStep) * frameStep;
|
|
371
|
+
const capped = Math.min(config.maxFrames ?? snapped, snapped);
|
|
372
|
+
return Math.max(config.minFrames ?? capped, capped);
|
|
287
373
|
}
|
|
288
374
|
//# sourceMappingURL=videoSettings.js.map
|