Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text t
.claude/skills/aiskillstore-ai-video-generation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 38% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 32% | 0% |
Generate videos with 40+ AI models via inference.sh CLI.
> Requires inference.sh CLI (infsh). Get installation instructions: npx skills add inference-sh/skills@agent-tools
bashinfsh login # Generate a video with Veo infsh app run google/veo-3-1-fast --input '{"prompt": "drone shot flying over a forest"}'
| Model | App ID | Best For | |-------|--------|----------| | Veo 3.1 Fast | google/veo-3-1-fast | Fast, with optional audio | | Veo 3.1 | google/veo-3-1 | Best quality, frame interpolation | | Veo 3 | google/veo-3 | High quality with audio | | Veo 3 Fast | google/veo-3-fast | Fast with audio | | Veo 2 | google/veo-2 | Realistic videos | | Grok Video | xai/grok-imagine-video | xAI, configurable duration | | Seedance 1.5 Pro | bytedance/seedance-1-5-pro | With first-frame control | | Seedance 1.0 Pro | bytedance/seedance-1-0-pro | Up to 1080p |
| Model | App ID | Best For | |-------|--------|----------| | Wan 2.5 | falai/wan-2-5 | Animate any image | | Wan 2.5 I2V | falai/wan-2-5-i2v | High quality i2v | | Seedance Lite | bytedance/seedance-1-0-lite | Lightweight 720p |
| Model | App ID | Best For | |-------|--------|----------| | OmniHuman 1.5 | bytedance/omnihuman-1-5 | Multi-character | | OmniHuman 1.0 | bytedance/omnihuman-1-0 | Single character | | Fabric 1.0 | falai/fabric-1-0 | Image talks with lipsync | | PixVerse Lipsync | falai/pixverse-lipsync | Realistic lipsync |
| Tool | App ID | Description | |------|--------|-------------| | HunyuanVideo Foley | infsh/hunyuanvideo-foley | Add sound effects to video | | Topaz Upscaler | falai/topaz-video-upscaler | Upscale video quality | | Media Merger | infsh/media-merger | Merge videos with transitions |
bashinfsh app list --category video
bashinfsh app run google/veo-3-1-fast --input '{ "prompt": "A timelapse of a flower blooming in a garden" }'
bashinfsh app run xai/grok-imagine-video --input '{ "prompt": "Waves crashing on a beach at sunset", "duration": 5 }'
bashinfsh app run falai/wan-2-5 --input '{ "image_url": "https://your-image.jpg" }'
bashinfsh app run bytedance/omnihuman-1-5 --input '{ "image_url": "https://portrait.jpg", "audio_url": "https://speech.mp3" }'
bashinfsh app run falai/fabric-1-0 --input '{ "image_url": "https://face.jpg", "audio_url": "https://audio.mp3" }'
bashinfsh app run falai/pixverse-lipsync --input '{ "image_url": "https://portrait.jpg", "audio_url": "https://speech.mp3" }'
bashinfsh app run falai/topaz-video-upscaler --input '{"video_url": "https://..."}'
bashinfsh app run infsh/hunyuanvideo-foley --input '{ "video_url": "https://silent-video.mp4", "prompt": "footsteps on gravel, birds chirping" }'
bashinfsh app run infsh/media-merger --input '{ "videos": ["https://clip1.mp4", "https://clip2.mp4"], "transition": "fade" }'
bash# Full platform skill (all 150+ apps) npx skills add inference-sh/skills@agent-tools # Google Veo specific npx skills add inference-sh/skills@google-veo # AI avatars & lipsync npx skills add inference-sh/skills@ai-avatar-video # Text-to-speech (for video narration) npx skills add inference-sh/skills@text-to-speech # Image generation (for image-to-video) npx skills add inference-sh/skills@ai-image-generation # Twitter (post videos) npx skills add inference-sh/skills@twitter-automation
Browse all apps: infsh app list
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 7,818 | 15,661 | +100% | 1 | 1 | 0% | 1,454 | 2,010 | +38% | 0 | 0 | — |
case-02 | fail→pass | 6,238 | 14,338 | +130% | 1 | 1 | 0% | 1,140 | 1,961 | +72% | 0 | 0 | — |
case-03 | fail→pass | 13,675 | 2,814 | -79% | 1 | 1 | 0% | 2,698 | 2,098 | -22% | 0 | 0 | — |
case-04 | pass→pass | 5,768 | 4,305 | -25% | 1 | 1 | 0% | 1,171 | 2,297 | +96% | 0 | 0 | — |
case-05 | pass→pass | 9,641 | 26,685 | +177% | 1 | 1 | 0% | 1,884 | 3,078 | +63% | 0 | 0 | — |
case-06 | pass→pass | 25,847 | 13,130 | -49% | 1 | 1 | 0% | 3,424 | 4,343 | +27% | 0 | 0 | — |
case-07 | fail→pass | 10,439 | 2,655 | -75% | 1 | 1 | 0% | 1,800 | 1,996 | +11% | 0 | 0 | — |
case-08 | fail→pass | 7,802 | 2,088 | -73% | 1 | 1 | 0% | 1,449 | 1,915 | +32% | 0 | 0 | — |
case-09 | pass→pass | 13,542 | 3,965 | -71% | 1 | 1 | 0% | 1,342 | 1,980 | +48% | 0 | 0 | — |
case-10 | fail→pass | 10,819 | 4,985 | -54% | 1 | 1 | 0% | 2,130 | 1,863 | -13% | 0 | 0 | — |
case-11 | fail→pass | 7,313 | 2,051 | -72% | 1 | 1 | 0% | 1,313 | 1,868 | +42% | 0 | 0 | — |
case-12 | fail→pass | 6,738 | 1,991 | -70% | 1 | 1 | 0% | 1,375 | 1,900 | +38% | 0 | 0 | — |
case-13 | fail→pass | 9,870 | 1,800 | -82% | 1 | 1 | 0% | 2,151 | 1,850 | -14% | 0 | 0 | — |
case-14 | fail→pass | 9,360 | 2,341 | -75% | 1 | 1 | 0% | 1,722 | 1,952 | +13% | 0 | 0 | — |
case-15 | fail→pass | 6,507 | 2,380 | -63% | 1 | 1 | 0% | 1,221 | 1,955 | +60% | 0 | 0 | — |
case-16 | fail→pass | 13,994 | 1,882 | -87% | 1 | 1 | 0% | 2,273 | 1,824 | -20% | 0 | 0 | — |
case-17 | fail→pass | 5,143 | 2,851 | -45% | 1 | 1 | 0% | 1,009 | 2,033 | +101% | 0 | 0 | — |
case-18 | fail→pass | 4,918 | 2,730 | -44% | 1 | 1 | 0% | 966 | 2,017 | +109% | 0 | 0 | — |
case-19 | fail→pass | 5,550 | 2,113 | -62% | 1 | 1 | 0% | 1,001 | 1,819 | +82% | 0 | 0 | — |
case-20 | fail→pass | 4,853 | 1,687 | -65% | 1 | 1 | 0% | 865 | 1,746 | +102% | 0 | 0 | — |
case-21 | fail→pass | 6,899 | 2,022 | -71% | 1 | 1 | 0% | 1,161 | 1,809 | +56% | 0 | 0 | — |
case-22 | fail→pass | 6,366 | 1,952 | -69% | 1 | 1 | 0% | 1,067 | 1,840 | +72% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +82 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.