Hugging Face releases Diffusers 0.42.0 with support for FLUX.3 and Bria Fibo 2.0

Hugging Face has released Diffusers 0.42.0. This release adds FLUX.3 Image Klein, Bria Fibo 2.0, Kandinsky 6, SANA-WM, and RFD4-Proteína, alongside new adapter support, hardware integrations, and modular pipelines. Python 3.11 or newer is now required.

FLUX.3 Image Klein from Black Forest Labs supports text-to-image generation and editing with one or more reference images. Both the base and step-distilled checkpoints are available through ModularPipeline, which includes an integrated prompt upsampler that turns short requests into detailed captions and supports layout instructions with bounding boxes. The integration also includes single-file transformer loading and BFL FP8r and NVFP4 checkpoints.

Bria Fibo 2.0 supports image generation from structured JSON captions and editing with up to five reference images through BriaFibo2Pipeline. The integration includes the dev checkpoint and the edit-turbo checkpoint, which runs in four steps without classifier-free guidance. LoRA loading and DreamBooth LoRA training examples for text-to-image and image editing are also included.