
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 filtersReads the text in an image and returns it as plain text
florence-2-large/caption-to-phrase-groundingImage Editing
≈ $0.003
Integrate
florence-2-large/dense-region-captionImage Editing
≈ $0.004
Integrate
florence-2-large/object-detectionImage Editing
≈ $0.003
Integrate
florence-2-large/ocr-with-regionImage Editing
≈ $0.004
Integrate
florence-2-large/open-vocabulary-detectionImage Editing
≈ $0.003
Integrate
florence-2-large/referring-expression-segmentationImage Editing
≈ $0.005
Integrate
florence-2-large/region-proposalImage Editing
≈ $0.003
Integrate
florence-2-large/region-to-segmentationImage Editing
≈ $0.009
Integrate
florence-2-large/captionVision
≈ $0.003
Integrate
florence-2-large/detailed-captionVision
≈ $0.004
Integrate
florence-2-large/ocrVision
≈ $0.003
Integrate
florence-2-large/region-to-categoryVision
≈ $0.003
Integrate
florence-2-large/more-detailed-captionVision
≈ $0.004
Integrate
florence-2-large/region-to-descriptionVision
≈ $0.003
Integrate