◐ModelVision & ImageFree
FLUX.1
State-of-the-art rectified-flow transformer text-to-image models from Black Forest Labs; the [schnell] variant is Apache-2.0.
FLUX.1
FLUX.1 is a family of state-of-the-art text-to-image models from Black Forest Labs, the team behind Stable Diffusion. This is the official inference repository. Built as a 12B-parameter rectified-flow transformer, FLUX.1 sets a high bar for prompt adherence, typography, and image fidelity among open image models.
Key features
- 12B-parameter rectified-flow transformer for high-fidelity text-to-image
- Variants: [schnell] (fast, few-step, Apache-2.0), [dev] (guidance-distilled), and [pro]
- Strong prompt following, legible text rendering, and coherent anatomy
- Reference sampling code, CLI, and a Streamlit demo
- First-class Hugging Face
diffusersintegration
License note: the inference code in this repository is Apache-2.0 and the FLUX.1 [schnell] weights are Apache-2.0; the [dev] weights carry a separate non-commercial license, so check the model card before commercial use.
Curated mirror of the open-source FLUX.1 (Apache-2.0). Get it from the source.