← back to the directory
Model Inference & Serving

FLUX.1

1Black 2Forest 3Labs' 4rectified-flow 5text-to-image 6model

the six Ws · specification

W1 Who

Black Forest Labs, founded by former Stable Diffusion creators, developed the FLUX.1 image model family.

W2 What

FLUX.1 is a 12B-parameter rectified-flow diffusion transformer for text-to-image generation, released in schnell, dev, and pro variants.

W3 Where

Weights for schnell and dev are hosted on Hugging Face, with inference code on GitHub.

W4 When

Released August 2024 by Black Forest Labs.

W5 Why

Built to push open and commercial text-to-image quality and prompt adherence beyond prior diffusion models.

W6 With

Runs via the black-forest-labs/flux GitHub repo, ComfyUI, or Diffusers with the released checkpoints.

W7 Watch

FLUX.1 schnell is Apache 2.0, dev is non-commercial only, pro and flex are proprietary API only; maintained by Black Forest Labs.

text-to-imagediffusion-transformeropen-weightsimage-generationrectified-flow

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.