FLUX – The First Ever Open Source text-2-image text-2-video model and ComfyUI implementation

FLUX (or FLUX. 1) is a suite of text-to-image models from Black Forest Labs, a new company set up by some of the AI researchers behind innovations and models like VQGAN, Stable Diffusion, Latent Diffusion, and Adversarial Diffusion Distillation

https://fal.ai/models/fal-ai/flux

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

It comes in three models:

  • FLUX.1 [dev]: The base model, open-sourced with a non-commercial license for community to build on top of
  • FLUX.1 [schnell]: A distilled version of the base model that operates up to 10 times faster. Apache 2 Licensed.
  • FLUX.1 [pro]: A closed-source version only available through API. https://docs.bfl.ml/

ComfyUI implementation :

https://comfyanonymous.github.io/ComfyUI_examples/flux

https://github.com/camenduru/comfyui-colab/blob/main/workflow/flux_image_to_image.json

https://www.patreon.com/posts/106135985

https://stable-diffusion-art.com/flux-comfyui/