image-to-video
ByteDance Seedance v1 Lite converts 1 to 4 reference images into high-quality videos with reference-to-video image-to-video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Input
Idle
Your request will cost $0.18 per run.
For $10 you can run this model approximately 55 times.
One more thing::
ExamplesView all
README
ByteDance Seedance V1 Lite — Reference-to-Video
Seedance V1 Lite Reference-to-Video is an advanced multi-reference video generation model from ByteDance that creates videos featuring subjects from your reference images. Upload up to 4 reference images of people, animals, or objects, and the model generates a coherent video with those subjects interacting based on your prompt.
Why It Stands Out
- Multi-reference support: Add up to 4 reference images to include multiple subjects in your video.
- Subject preservation: Maintains the identity and appearance of subjects from reference images.
- Prompt-guided action: Describe how subjects should interact or move in the generated video.
- Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
- Camera control: Option to fix camera position for stable, static shots.
- Flexible duration: Generate videos of varying lengths based on your needs.
- Reproducibility: Use the seed parameter to recreate exact results.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video action and scene. |
| reference_images | Yes | Up to 4 reference images of subjects to include (upload or URL). |
| duration | No | Video length in seconds (default: 5). |
| camera_fixed | No | Fix camera position for stable shots. |
| seed | No | Set for reproducibility; leave empty for random. |
How to Use
- Write a prompt describing the action and scene you want. Use the Prompt Enhancer for AI-assisted optimization.
- Add reference images — upload up to 4 images of subjects (people, animals, objects) to include in the video.
- Set duration — choose how long you want the video to be.
- Enable camera_fixed (optional) — check this for a stable, static camera shot.
- Set a seed (optional) for reproducible results.
- Click Run and wait for your video to generate.
- Preview and download the result.
Best Use Cases
- Character Animation — Animate portraits or character images in custom scenes.
- Pet Videos — Create fun videos featuring your pets in imaginative scenarios.
- Social Media Content — Generate engaging videos with multiple subjects interacting.
- Storytelling — Bring characters together in narrative video clips.
- Marketing & Advertising — Create product videos featuring specific items or mascots.
- Creative Projects — Combine different subjects in unique, creative compositions.
Pricing
| Duration | Price |
|---|---|
| 5 seconds | $0.18 |
| 10 seconds | $0.36 |
| 15 seconds | $0.54 |
| 20 seconds | $0.72 |
Total cost = $0.18 × (duration / 5)
Pro Tips for Best Quality
- Use clear, high-quality reference images with subjects well-visible.
- For best results, use front-facing or 3/4 angle reference photos.
- Be specific in your prompt about how subjects should interact.
- Enable camera_fixed for professional-looking static shots.
- When using multiple subjects, describe their relative positions and actions clearly.
- Fix the seed when iterating to compare different prompt variations.
Notes
- Maximum of 4 reference images per generation.
- Ensure uploaded image URLs are publicly accessible.
- Processing time varies based on duration and current queue load.
- Please ensure your content complies with usage guidelines.