FLUX.2 klein
Black Forest Labs' sub-second image generation — generate and edit in <0.5s
Black Forest Labs' sub-second image generation: generate and edit images in under 0.5 seconds.
Image generation and computer vision — detection, editing, 3D.
Key features
- Minimal inference code to run image generation and editing with FLUX open-weight models
- Extensive open-weight suite: FLUX.1 schnell/dev, Fill, Canny, Depth, Redux, Kontext, Krea
- Supports text-to-image, in/out-painting, structural conditioning, image variation, image
- Optional TensorRT installation support for accelerated inference
- API access for all models including Pro tier via docs.bfl.ai
Good for
- Running FLUX image models locally with minimal setup
- Image editing and structural-conditioned generation with open weights
Stack & tags
Pythonimage-generationtext-to-imageimage-editingopen-weightsfluxdiffusionpytorch
Quick start
cd $HOME && git clone https://github.com/black-forest-labs/flux
cd $HOME/flux
python3.10 -m venv .venv
source .venv/bin/activate
pip install -e ".[all]"From the project README on GitHub.
Similar open-source projects
DiffSynth-Studio
★ 13,200The framework behind Qwen-Image-i2L — the first "Image→LoRA" visual generation system
TRELLIS.2
★ 12,083Native and Compact Structured Latents for 3D Generation