Gemini Omni Flash 1.2
Text to video · Image to video · Video editing
Starting price $0.0433 / second
By Black Forest Labs
Black Forest Labs' FLUX.3 edits a video from a written instruction, extends a clip, and makes new clips from text, one image, a first and last frame or keyframes.
blackforestlabs/flux-3/edit-videoThis model has other modes with their own ids: blackforestlabs/flux-3/extend-video, blackforestlabs/flux-3/extend-video/draft, blackforestlabs/flux-3/first-last-frame-to-video, blackforestlabs/flux-3/first-last-frame-to-video/draft, blackforestlabs/flux-3/image-to-video, blackforestlabs/flux-3/image-to-video/draft, blackforestlabs/flux-3/keyframes-to-video, blackforestlabs/flux-3/keyframes-to-video/draft, blackforestlabs/flux-3/text-to-video, blackforestlabs/flux-3/text-to-video/draft.
Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "blackforestlabs/flux-3/edit-video",
"input": {
"prompt": "Turn the street scene into a snowy winter evening with falling snow and cold blue light. Keep the people, their clothes and the camera movement unchanged.",
"video_url": "https://example.com/input.mp4"
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "blackforestlabs/flux-3/edit-video", "quote_id": "QUOTE_ID", "input": {"prompt":"Turn the street scene into a snowy winter evening with falling snow and cold blue light. Keep the people, their clothes and the camera movement unchanged.","video_url":"https://example.com/input.mp4"}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
promptrequired | string | The text prompt describing how to change the input video. The clip is re-rendered preserving motion, timing, and framing. |
safety_tolerance | integer | The safety tolerance level for the generated video. 0 is the strictest and 4 is the most permissive. |
video_urlrequired | string (URL) | URL of the input video. MP4, under 50 MB and under 15 seconds. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
The edit mode re-renders an MP4 under 15 seconds from your instruction and keeps its motion, timing and framing. Other modes continue a clip from its last frames, animate one image, go from a start image to an end image, pass through up to 10 keyframes, or start from text alone.
Full renders last 5 to 20 seconds at 720p or 1080p, with generated sound you can switch off. Draft versions of most modes let you try an idea before the full render.
Compare the beginning, middle and ending with the original clip. Check faces, clothing, motion, timing and whether the requested change flickers between frames. Listen to the output before using it; do not assume the source soundtrack has been preserved.