Black Forest Labs FLUX 3 Video (Video-to-Video)
FLUX 3 Video continues your clip from its last frames for 5-15 s, carrying on its motion, camera and scene, with sound.
FLUX 3 Video, from Black Forest Labs, continues a clip you give it for 5-15 seconds. Sound comes with the picture: speech in several languages with lipsync, effects and ambience (put a spoken line in quotes in the prompt); a prompt can hold several shots. Clips are 24 fps, in HD up to 4K (3840 x 2176 at 16:9).
The new footage picks up from the clip's final frames and carries on its motion, camera and scene. Use it to extend a shot or a scene. It does not edit or restyle the clip you give it. Video-to-video is dearer than a new video.
Inputs: prompt (required); start_video (required, an MP4 link or upload); duration (whole seconds, 5-15, default 5); resolution (hd by default, fhd, qhd, uhd); aspect_ratio (auto, or one of 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21); generate_audio (on by default); safety_tolerance (0 strictest to 4, default 2).
Price per second of video: hd $0.21, fhd $0.27, qhd $0.31, uhd $0.45. The default 5 s at hd is $1.05. Partial seconds are charged as whole seconds and sound is free. It makes no drafts. A request that fails or is stopped by content moderation is not charged.
- Image to Video
Price: From $0.21 per second of duration, depending on resolution; whole seconds of video, 5-15 s, sound free. One run with default settings costs $1.05.
Run Black Forest Labs FLUX 3 Video (Video-to-Video) via API
curl -X POST https://api.flymy.ai/api/v1/flymyai/flux-3-video-v2v/predict \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"The camera slowly pulls back to reveal the whole miniature city while the tiny figures keep walking","start_video":"https://storage.googleapis.com/open-inference-results/agent-files/1585/40ecb0fd73ed4b5eb3b34b53b3b7e290/bytedance-seedance-2_0-fast-text-to-video_a64b.mp4","duration":5,"resolution":"hd"}'API documentation · Create a free account · Pricing