Run FLUX.2 on Replicate
FLUX.2 brings professional-grade image generation and editing with unprecedented detail, multi-reference support, and enterprise efficiency.
FLUX.2 brings professional-grade image generation and editing with unprecedented detail, multi-reference support, and enterprise efficiency.
A deep-dive into the Taylor Seer optimization technique
We hosted a hackathon with BFL for FLUX.1 Kontext. Here were the winners.
Add trt support for BF16 (#195) * fix interface of `get_sample_input` * save configuration parameters * ae wrapper implemented * fix import * add AEWrapper step…
fix: correct link in readme (#393) * fix: correct link in readme * docs: add conda scripts * docs: format readme
Update structural-conditioning.md to include a diffusers note (#395)
Ruff ci (#194) * apply ruff * rename * specify ruff version for CI * also check imports * check formatting
FLUX is Black Forest Labs' image-generation family — FLUX.1 [pro / dev / schnell]. The open-weight state-of-the-art on image quality after Stable Diffusion 3.5, founded by the original Stable Diffusion authors.
Owner: Black Forest Labs. We have 7 stories indexed for this model, auto-tagged from titles across every tracked source — official announcements, papers, GitHub release notes, and third-party press. The CTA on each card links to the original; the official site is bfl.ai.
Related image models: Stable Diffusion, Midjourney, Imagen.