[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2222":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":9,"rankLanguage":9,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":9,"pushedAt":9,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":15,"starSnapshotCount":15,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},2222,"flux","black-forest-labs\u002Fflux","black-forest-labs","Official inference repo for FLUX.1 models",null,"Python",25608,1891,198,203,0,1,17,89,5,44.83,"Apache License 2.0",false,"main",true,[],"2026-06-12 02:00:38","# FLUX\nby Black Forest Labs: https:\u002F\u002Fbfl.ai.\n\nDocumentation for our API can be found here: [docs.bfl.ai](https:\u002F\u002Fdocs.bfl.ai\u002F).\n\n![grid](assets\u002Fgrid.jpg)\n\nThis repo contains minimal inference code to run image generation & editing with our Flux open-weight models.\n\n## Local installation\n\n```bash\ncd $HOME && git clone https:\u002F\u002Fgithub.com\u002Fblack-forest-labs\u002Fflux\ncd $HOME\u002Fflux\npython3.10 -m venv .venv\nsource .venv\u002Fbin\u002Factivate\npip install -e \".[all]\"\n```\n\n### Local installation with TensorRT support\n\nIf you would like to install the repository with [TensorRT](https:\u002F\u002Fgithub.com\u002FNVIDIA\u002FTensorRT) support, you currently need to install a PyTorch image from NVIDIA instead. First install [enroot](https:\u002F\u002Fgithub.com\u002FNVIDIA\u002Fenroot), next follow the steps below:\n\n```bash\ncd $HOME && git clone https:\u002F\u002Fgithub.com\u002Fblack-forest-labs\u002Fflux\nenroot import 'docker:\u002F\u002F$oauthtoken@nvcr.io#nvidia\u002Fpytorch:25.01-py3'\nenroot create -n pti2501 nvidia+pytorch+25.01-py3.sqsh\nenroot start --rw -m ${PWD}\u002Fflux:\u002Fworkspace\u002Fflux -r pti2501\ncd flux\npip install -e \".[tensorrt]\" --extra-index-url https:\u002F\u002Fpypi.nvidia.com\n```\n\n### Open-weight models\n\nWe are offering an extensive suite of open-weight models. For more information about the individual models, please refer to the link under **Usage**.\n\n| Name                        | Usage                                                      | HuggingFace repo                                               | License                                                               |\n| --------------------------- | ---------------------------------------------------------- | -------------------------------------------------------------- | --------------------------------------------------------------------- |\n| `FLUX.1 [schnell]`          | [Text to Image](docs\u002Ftext-to-image.md)                     | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-schnell        | [apache-2.0](model_licenses\u002FLICENSE-FLUX1-schnell)                    |\n| `FLUX.1 [dev]`              | [Text to Image](docs\u002Ftext-to-image.md)                     | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-dev            | [FLUX.1-dev Non-Commercial License](model_licenses\u002FLICENSE-FLUX1-dev) |\n| `FLUX.1 Fill [dev]`         | [In\u002FOut-painting](docs\u002Ffill.md)                            | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-Fill-dev       | [FLUX.1-dev Non-Commercial License](model_licenses\u002FLICENSE-FLUX1-dev) |\n| `FLUX.1 Canny [dev]`        | [Structural Conditioning](docs\u002Fstructural-conditioning.md) | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-Canny-dev      | [FLUX.1-dev Non-Commercial License](model_licenses\u002FLICENSE-FLUX1-dev) |\n| `FLUX.1 Depth [dev]`        | [Structural Conditioning](docs\u002Fstructural-conditioning.md) | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-Depth-dev      | [FLUX.1-dev Non-Commercial License](model_licenses\u002FLICENSE-FLUX1-dev) |\n| `FLUX.1 Canny [dev] LoRA`   | [Structural Conditioning](docs\u002Fstructural-conditioning.md) | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-Canny-dev-lora | [FLUX.1-dev Non-Commercial License](model_licenses\u002FLICENSE-FLUX1-dev) |\n| `FLUX.1 Depth [dev] LoRA`   | [Structural Conditioning](docs\u002Fstructural-conditioning.md) | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-Depth-dev-lora | [FLUX.1-dev Non-Commercial License](model_licenses\u002FLICENSE-FLUX1-dev) |\n| `FLUX.1 Redux [dev]`        | [Image variation](docs\u002Fimage-variation.md)                 | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-Redux-dev      | [FLUX.1-dev Non-Commercial License](model_licenses\u002FLICENSE-FLUX1-dev) |\n| `FLUX.1 Kontext [dev]`      | [Image editing](docs\u002Fimage-editing.md)                     | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-Kontext-dev    | [FLUX.1-dev Non-Commercial License](model_licenses\u002FLICENSE-FLUX1-dev) |\n| `FLUX.1 Krea [dev]`         | [Text to Image](docs\u002Ftext-to-image.md)                     | https:\u002F\u002Fhuggingface.co\u002Fblack-forest-labs\u002FFLUX.1-Krea-dev       | [FLUX.1-dev Non-Commercial License](model_licenses\u002FLICENSE-FLUX1-dev) |\n\nThe weights of the autoencoder are also released under [apache-2.0](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fchoosealicense\u002Flicenses\u002Fblob\u002Fmain\u002Fmarkdown\u002Fapache-2.0.md) and can be found in the HuggingFace repos above.\n\n## API usage\n\nOur API offers access to all models including our Pro tier non-open weight models. Check out our API documentation [docs.bfl.ai](https:\u002F\u002Fdocs.bfl.ai\u002F) to learn more.\n\n## Licensing models for commercial use\n\nYou can license our models for commercial use here: https:\u002F\u002Fbfl.ai\u002Fpricing\u002Flicensing\n\nAs the fee is based on a monthly usage, we provide code to automatically track your usage via the BFL API. To enable usage tracking please select *track_usage* in the cli or click the corresponding checkmark in our provided demos.\n\n### Example: Using FLUX.1 Kontext with usage tracking\n\nWe provide a reference implementation for running FLUX.1 with usage tracking enabled for commercial licensing.\nThis can be customized as needed as long as the usage reporting is accurate.\n\nFor the reporting logic to work you will need to set your API key as an environment variable before running:\n```bash\nexport BFL_API_KEY=\"your_api_key_here\"\n```\n\nYou can call `FLUX.1 Kontext [dev]` like this with tracking activated:\n\n```bash\npython -m flux kontext --track_usage --loop\n```\n\nFor a single generation:\n\n```bash\npython -m flux kontext --track_usage --prompt \"replace the logo with the text 'Black Forest Labs'\"\n```\n\nThe above reporting logic works similarly for FLUX.1 [dev] and FLUX.1 Tools [dev].\n\n**Note that this is only required when using one or more of our open weights models commercially. More information on the commercial licensing can be found at the [BFL Helpdesk](https:\u002F\u002Fhelp.bfl.ai\u002Fcollections\u002F6939000511-licensing).**\n\n\n## Citation\n\nIf you find the provided code or models useful for your research, consider citing them as:\n\n```bib\n@misc{labs2025flux1kontextflowmatching,\n      title={FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space},\n      author={Black Forest Labs and Stephen Batifol and Andreas Blattmann and Frederic Boesel and Saksham Consul and Cyril Diagne and Tim Dockhorn and Jack English and Zion English and Patrick Esser and Sumith Kulal and Kyle Lacey and Yam Levi and Cheng Li and Dominik Lorenz and Jonas Müller and Dustin Podell and Robin Rombach and Harry Saini and Axel Sauer and Luke Smith},\n      year={2025},\n      eprint={2506.15742},\n      archivePrefix={arXiv},\n      primaryClass={cs.GR},\n      url={https:\u002F\u002Farxiv.org\u002Fabs\u002F2506.15742},\n}\n\n@misc{flux2024,\n    author={Black Forest Labs},\n    title={FLUX},\n    year={2024},\n    howpublished={\\url{https:\u002F\u002Fgithub.com\u002Fblack-forest-labs\u002Fflux}},\n}\n```\n","FLUX 是一个用于图像生成和编辑的推理库。它提供了多种基于开放权重模型的图像处理功能，支持从文本到图像的转换、图像填充及结构条件生成等任务。项目采用Python编写，并支持TensorRT加速以提高性能。用户可以通过简单的本地安装步骤快速上手使用这些模型。此外，该项目还提供了详细的文档和示例代码来帮助开发者更好地理解和应用这些技术。FLUX适合需要进行高质量图像合成或编辑的应用场景，如创意设计、内容创作等领域。",2,"2026-06-11 02:48:55","top_language"]