FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. This model offers cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.
https://api.deepinfra.com/v1/openai/images$0.0005 per image unit (1024x1024 default)
| Model | Max resolution | Resolutions | Aspect ratios | Batch size |
|---|---|---|---|---|
| FLUX-1-dev | — | — | — | — |
| FLUX-1-Redux-dev | — | — | — | — |
| FLUX-1-schnell | — | — | — | — |
| FLUX-1.1-pro | — | — | — | — |
| FLUX-pro | — | — | — | — |
| FLUX.1-Kontext-dev | — | — | — | — |
| flux | — | — | — | — |
/v1/models/deepinfra/black-forest-labs/FLUX-1-schnellFLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. This model offers cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.