flux is an image generation and editing tool that provides official inference code for FLUX.1 models. It supports local installation and offers various open-weight models for diverse creative tasks.
flux is the official inference repository for FLUX.1 models, enabling users to perform image generation and editing tasks. It provides minimal inference code for running these operations locally, with support for both standard and TensorRT installations. The tool offers an extensive suite of open-weight models, including those for text-to-image generation, in/out-painting, structural conditioning (Canny, Depth), image variation, and image editing. Users can access these models via HuggingFace and utilize a provided API for broader access, including Pro tier non-open weight models. Commercial licensing options are available, with code provided for usage tracking via the BFL API, making it suitable for developers and researchers looking to integrate advanced AI image capabilities into their projects.
Best used for
Ideal for graphic designers and researchers who need to generate new images from text, edit existing images with in/out-painting, and apply structural conditioning for precise control. Especially valuable for those integrating advanced AI image capabilities into their projects or conducting research with open-weight models.
Common actions
generate images
edit images
create visuals
apply structural conditions
vary images
face swappingdeepfakeopen-sourceautomated workflowcollaborationworkflowslow-code/no-codegithub copilot"AI Agents"
Capabilities
Key features
Image generation
Image editing
Text-to-image
In/out-painting
Structural conditioning
Image variation
Local inference
Target Audience
graphic designerpainter
Integrations
Not yet documented
Pricing & Plans
Open Source · Paid · Usage-based
Free
FAQs
What types of image generation and editing models are available in flux?
flux offers a comprehensive suite of open-weight models, including FLUX.1 [schnell] for text-to-image, FLUX.1 Fill [dev] for in/out-painting, and FLUX.1 Canny/Depth [dev] for structural conditioning. It also includes models for image variation (FLUX.1 Redux [dev]) and image editing (FLUX.1 Kontext [dev]).
Can flux models be used for commercial purposes?
Yes, flux models can be licensed for commercial use. Black Forest Labs provides a licensing portal where fees are based on monthly usage. The repository includes code to automatically track usage via the BFL API for accurate reporting.
Does flux support local installation with GPU acceleration?
Yes, flux supports local installation with TensorRT for GPU acceleration. This requires installing a PyTorch image from NVIDIA and following specific steps to set up the environment, enabling faster inference for image generation and editing tasks.
Shypd.aiThe largest open index of AI tools
