FLUX.1 [schnell] (German for “fast”) is a text-to-image generation model by Black Forest Labs. It is the speed-optimized / distilled version of the FLUX.1 family. It has approximately 12 billion parameters (12B), uses a rectified flow transformer architecture, and is trained via latent adversarial diffusion distillation so that high-quality images can be generated in very few inference steps (1 to 4 steps). It is released under the Apache-2.0 license, allowing personal, scientific, and commercial use.
Please login to use description