Vidu
Vidu Q1 and Q2 video lines with 2-8s duration control, plus reference-to-image and text-to-image endpoints.
Studio is in early access; availability resolves per project after sign-in.
- Endpoints
- 21
- Eligible
- 21
- Input schemas imported
- 21 / 21
- Delivery
- fal.ai
- Weights
- Not stated
- Developer
- Not stated in source
Overview
Vidu's Q2 Pro image-to-video delivers 2-8 second generations adjustable in 1-second increments for precise timing control. Advertising, social, and prototyping uses target exact-length delivery. Q2 reference-to-image handles up to 3 references for character consistency; a text-to-image endpoint covers single frames in three aspect ratios. Q1 image, reference, start-end, and text-to-video lines join the family.
Capabilities
- 2-8s 1s-step durations
- 3-reference consistency
- Single-frame text-to-image tier
- Q1 multi-line breadth
Best for
- Social media content
- Product demonstrations
- Creative prototyping
Use cases
- Exact-length ads
- Consistent-character shots
- Timed social clips
Endpoints
21 eligible. Cataloged is not the same as executable: Studio resolves which endpoints a project can run.
| Endpoint | Task | Catalog status | Inputs |
|---|---|---|---|
fal-ai/vidu/image-to-video | image to video | Eligible | 4 fields · requires prompt, image_url |
fal-ai/vidu/q1/image-to-video | image to video | Eligible | 4 fields · requires prompt, image_url |
fal-ai/vidu/q1/reference-to-video | reference to video | Eligible | 6 fields · requires prompt, reference_image_urls |
fal-ai/vidu/q1/start-end-to-video | video editing | Eligible | 5 fields · requires prompt, start_image_url, end_image_url |
fal-ai/vidu/q1/text-to-video | text to video | Eligible | 5 fields · requires prompt |
fal-ai/vidu/q2/image-to-video/pro | image to video | Eligible | 8 fields · requires prompt, image_url |
fal-ai/vidu/q2/image-to-video/turbo | image to video | Eligible | 8 fields · requires prompt, image_url |
fal-ai/vidu/q2/reference-to-image | image generation | Eligible | 4 fields · requires prompt, reference_image_urls |
fal-ai/vidu/q2/reference-to-video/pro | reference to video | Eligible | 9 fields · requires prompt |
fal-ai/vidu/q2/text-to-image | text to image | Eligible | 3 fields · requires prompt |
fal-ai/vidu/q2/text-to-video | text to video | Eligible | 7 fields · requires prompt |
fal-ai/vidu/q2/video-extension/pro | video editing | Eligible | 5 fields · requires video_url |
fal-ai/vidu/q3/image-to-video | image to video | Eligible | 7 fields · requires image_url |
fal-ai/vidu/q3/image-to-video/turbo | image to video | Eligible | 7 fields · requires image_url |
fal-ai/vidu/q3/reference-to-video/mix | reference to video | Eligible | 7 fields · requires prompt, reference_image_urls |
fal-ai/vidu/q3/text-to-video | text to video | Eligible | 6 fields · requires prompt |
fal-ai/vidu/q3/text-to-video/turbo | text to video | Eligible | 6 fields · requires prompt |
fal-ai/vidu/reference-to-image | image generation | Eligible | 4 fields · requires prompt, reference_image_urls |
fal-ai/vidu/reference-to-video | reference to video | Eligible | 5 fields · requires prompt, reference_image_urls |
fal-ai/vidu/start-end-to-video | video editing | Eligible | 5 fields · requires prompt, start_image_url, end_image_url |
fal-ai/vidu/template-to-video | video editing | Eligible | 4 fields · requires input_image_urls |
Questions
Duration control?
2-8 seconds in 1 second steps.
Reference support?
Up to 3 images for consistency.