ByteDance V1.5
Seedance 1.5 Pro image- and text-to-video with start and end-frame conditioning and native audio.
Studio is in early access; availability resolves per project after sign-in.
- Endpoints
- 3
- Eligible
- 2
- Input schemas imported
- 3 / 3
- Delivery
- fal.ai
- Weights
- Not stated
- Developer
- Not stated in source
Overview
Seedance 1.5 Pro animates images into cinematic video with synchronized audio, generating motion, camera movement, dialogue, and sound design between frames. Start-frame conditioning sets composition, lighting, subject, and style; an optional end frame defines the landing, with the model building the motion path between. Native audio spans dialogue, effects, and ambient sound. The family also lists an OmniHuman v1.5 endpoint.
Capabilities
- Start and end-frame conditioned generation
- Native dialogue, SFX, and ambient audio
- Text-to-video broadcast-ready clips
- Character and product animation
Best for
- Photo animation
- Product reveals
- Scene transitions for ads and trailers
Use cases
- Storyboard-to-video motion tests
- Talking-head from headshots
- Social clips with sound
Endpoints
1 under review · 2 eligible. Cataloged is not the same as executable: Studio resolves which endpoints a project can run.
| Endpoint | Task | Catalog status | Inputs |
|---|---|---|---|
fal-ai/bytedance/omnihuman/v1.5 | unknown | Under review | 6 fields · requires image_url, audio_url |
fal-ai/bytedance/seedance/v1.5/pro/image-to-video | image to video | Eligible | 10 fields · requires prompt, image_url |
fal-ai/bytedance/seedance/v1.5/pro/text-to-video | text to video | Eligible | 8 fields · requires prompt |
Questions
How do end frames work?
Upload start and optional end images; the model animates the path between them.
What audio is included?
Dialogue, sound effects, ambient audio, and music rendered with the video.