--- base_model: - black-forest-labs/FLUX.2-klein-base-9B datasets: - ControlLight/Light100K language: - en - zh license: apache-2.0 library_name: diffusers pipeline_tag: image-to-image ---

Original Repository: ControlLight/ControlLight

# ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement [![arXiv](https://img.shields.io/badge/arXiv-2605.25569-b31b1b.svg)](https://arxiv.org/abs/2605.25569) [![Project Page](https://img.shields.io/badge/Project-Page-blue)](https://yfyang007.github.io/ControlLight/) [![GitHub Code](https://img.shields.io/badge/GitHub-Code-black)](https://github.com/yfyang007/ControlLight) [![Light100K](https://img.shields.io/badge/Light100K-Dataset-green)](https://huggingface.co/datasets/ControlLight/Light100K) [![Hugging Face](https://img.shields.io/badge/HuggingFace-Model-yellow)](https://huggingface.co/ControlLight/ControlLight)
ControlLight is presented in the paper **[ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement](https://huggingface.co/papers/2605.25569)**. ControlLight is a controllable low-light enhancement model built on top of **FLUX.2 [klein] 9B**. It is trained as a LoRA for continuous illumination enhancement, enabling users to adjust enhancement strength with a controllable parameter `alpha`. The model is designed to enhance low-light images while preserving the original scene structure, visual content, and fine-grained details. ## 🔥🔥🔥 News!! - **May 2026:** 👋 We release **ControlLight**, its model weights, inference and training code. - **May 2026:** 👋 We release **Light100K**, a continuous low-light enhancement dataset for controllable illumination learning. ## ⚡️ Model Usage ### Installation This project currently relies on the patched local `diffusers/` checkout from the ControlLight repository. ```bash git clone https://github.com/yfyang007/ControlLight.git cd ControlLight conda create -n controlight python=3.12 -y conda activate controlight python -m pip install --upgrade pip python -m pip install -e diffusers python -m pip install -r requirements.txt python -m pip install -e . ``` You can verify the environment with: ```bash bash scripts/predict.sh --help bash scripts/demo.sh --help bash -lc 'source scripts/project_env.sh; python run.py --help >/dev/null' ``` ### Inference with ControlLight ```bash bash scripts/predict.sh predict-image \ --input /path/to/input.jpg \ --output /path/to/output.png \ --model-path /path/to/FLUX.2-klein-base-9B \ --lora-path /path/to/controllight.safetensors \ --alpha 0.50 \ --num-inference-steps 20 \ --guidance-scale 1.0 \ --seed 42 \ --device cuda \ --torch-dtype bfloat16 ``` ### CLI Quick Start ```bash bash scripts/predict.sh predict-four \ --input /path/to/images \ --output /path/to/out_four \ --model-path /path/to/FLUX.2-klein-base-9B \ --lora-path /path/to/controllight.safetensors \ --num-inference-steps 20 \ --seed 42 \ --device cuda \ --torch-dtype bfloat16 ``` ### Recommended Inference Config - **Device:** `cuda` - **Torch dtype:** `bfloat16` - **Inference steps:** `20` - **Guidance scale:** `1.0` - **Recommended seed:** `42` - **Enhancement strength:** `alpha` in `[0, 1]`, where larger values produce stronger low-light enhancement. ### Example Settings | Task | Setting | | --- | --- | | Mild Low-light Enhancement | `alpha=0.25` | | Medium Low-light Enhancement | `alpha=0.50` | | Strong Low-light Enhancement | `alpha=0.75` | | Full Low-light Enhancement | `alpha=1.00` | | Custom Enhancement Sweep | `--alphas 0.20,0.40,0.60,0.80` | ## Additional Resources - **Project Page:** [ControlLight Project Page](https://yfyang007.github.io/ControlLight/) - **GitHub Repository:** [yfyang007/ControlLight](https://github.com/yfyang007/ControlLight) - **Model:** [ControlLight/ControlLight](https://huggingface.co/ControlLight/ControlLight) - **Dataset:** [ControlLight/Light100K](https://huggingface.co/datasets/ControlLight/Light100K) - **Base Model:** [black-forest-labs/FLUX.2-klein-base-9B](https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B) ## License and Disclaimer The code of ControlLight is intended to be released under the Apache License 2.0. ControlLight is built on top of **FLUX.2 [klein] 9B** and uses third-party components, datasets, and model assets. All underlying base models and third-party components remain governed by their original licenses and terms. Users must comply with all applicable upstream licenses when using this project. ## Citation If you find ControlLight useful in your research, please star and cite: ```bibtex @misc{yang2026controllightcontrollableconsistentgeneralizable, title={ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement}, author={Yufeng Yang and Jianzhuang Liu and Jisheng Chu and Yuqi Peng and Xianfang Zeng and Jiancheng Huang and Shifeng Chen}, year={2026}, eprint={2605.25569}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2605.25569}, } ```