video
Hunyuan Video
Open video model generating quality clips from text with motion diversity and stable alignment.
Studio is in early access; availability resolves per project after sign-in.
- Endpoints
- 2
- Eligible
- 2
- Input schemas imported
- 2 / 2
- Delivery
- fal.ai
- Weights
- Not stated
- Developer
- Not stated in source
Overview
Hunyuan Video generates videos from text descriptions through a simple API, positioned as an open model with visual quality, motion diversity, text-video alignment, and generation stability. It targets developers and creators building tools, content apps, and enterprise solutions. A video-to-video endpoint joins the base model.
Capabilities
- Text-to-video generation
- Motion-diverse stable output
- Simple API integration
- Video-to-video endpoint
Best for
- Creative tools
- Content applications
- Enterprise solutions
Use cases
- Prompt-to-video features
- Engaging video content
- Integrated generation workflows
Endpoints
2 eligible. Cataloged is not the same as executable: Studio resolves which endpoints a project can run.
| Endpoint | Task | Catalog status | Inputs |
|---|---|---|---|
fal-ai/hunyuan-video | video editing | Eligible | 7 fields · requires prompt |
fal-ai/hunyuan-video/video-to-video | video to video | Eligible | 9 fields · requires prompt, video_url |
Questions
Open model?
Described as open with quality, diversity, and stability.
Beyond text input?
A video-to-video endpoint is listed.