
FLUX.1 [dev] Variants: 5
The open-weights FLUX workhorse, sharper and more faithful to long prompts than schnell.
No matches. Try “video”, “FLUX” or “webhooks”.
Loading models…

The open-weights FLUX workhorse, sharper and more faithful to long prompts than schnell.

Precise local edits from one reference image, such as changing colors, adding objects or rewriting text.
Black Forest Labs' video model, 5 to 20 second clips with sound at 720p or 1080p.
Turns one portrait and a voice track into a talking, gesturing avatar video.
Topaz Labs' image upscaler with face recovery, denoise and sharpening, up to 4x.
Clean, commercially safe background removal for products and people.
No models match these filters
Clear filtersReplaces the people in a video with people from reference photos while keeping motion, camera and audio
minimax/h3-max/text-to-videoText to Video
from $0.0325 / second of output video
Integrate
minimax/h3-max/camera-controlsImage to Video
from $0.0325 / second5 s ≈ $0.163
Integrate
minimax/h3-max/image-to-videoImage to Video
from $0.0325 / second of output video
Integrate
minimax/h3-max/reference-to-videoReference to Video
from $0.05 / second of output video
Integrate
minimax/h3-max/insert-videoVideo to Video
from $0.05 / second5 s ≈ $0.25
Integrate
minimax/h3-max/extend-videoVideo to Video
from $0.05 / second of output video
Integrate
minimax/h3-max/recastVideo to Video
from $0.30 / second of input video
Integrate
minimax/h3-max/reframe-videoVideo to Video
from $0.05 / second of input video
Integrate
minimax/h3-max/relightVideo to Video
from $0.05 / second of input video
Integrate
minimax/h3-max/lip-sync/image-to-videoLipsync & Avatars
from $0.05 / second of input audio
Integrate