← All models
Flux 3 First Last Frame to Video Draft
flux-3-first-last-frame-to-video-draft
Video editby blackforestlabs
FLUX.3 is Black Forest Labs' frontier audio/video model. Generate fast, low-cost draft previews between a start and an end frame, with a reusable draft cache for full-quality enhancement.
Example
Details
- Accepts
- image
Pricing
- Price
- 3.75 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| promptrequired | string | The text prompt describing the draft video. |
| duration | integerenum: 5, 6, 7, 8, 9, 10… | Draft duration in whole seconds from 5 through 20. An explicit duration pins the two images to the video boundaries. |
| aspect_ratio | stringenum: auto, 21:9, 2:1, 16:9, 4:3, 1:1… | Aspect ratio of the generated draft. `auto` lets the model choose. |
| end_image_urlrequired | string | URL or data URI of the image used as the last frame of the draft. |
| generate_audio | boolean | Whether to generate audio for the draft video. |
| start_image_urlrequired | string | URL or data URI of the image used as the first frame of the draft. |
| safety_tolerance | integer | The safety tolerance level for the generated video. 0 is the strictest and 4 is the most permissive. |
Output
| Field | Type | Description |
|---|---|---|
| video | — | The draft video. |
| draft_cache | — | Durable encrypted cache bundle; pass it to `draft-enhance` for a full-quality render. |