We are excited to introduce Flux, the largest SOTA open source text-to-image model to date, brought to you by Black Forest Labs—the original team behind Stable Diffusion. Flux pushes the boundaries of creativity and performance with an impressive 12B parameters, delivering aesthetics reminiscent of Midjourney. To play around with

Flux is an open source 12B parameter text-to-image model by Black Forest Labs—the original team behind Stable Diffusion. Needs 24GB of VRAM to run.

FLUX.1 [dev]: The base model, open-sourced with a non-commercial license for community to build on top of. https://huggingface.co/black-forest-labs/FLUX.1-dev

FLUX.1 [schnell]: A distilled version of the base model that operates up to 10 times faster. Apache 2 Licensed. https://huggingface.co/black-forest-labs/FLUX.1-schnell

Blog: https://blackforestlabs.ai/announcing-black-forest-labs/

GitHub: https://github.com/black-forest-labs/flux