nunchaku-flux.1-krea-dev/README.md

base_model, base_model_relation, datasets, frameworks, language, license, license_link, license_name, tags, tasks

base_model	base_model_relation	datasets	frameworks	language	license	license_link	license_name	tags	tasks
black-forest-labs/FLUX.1-Krea-dev	quantized	mit-han-lab/svdquant-datasets	PyTorch	en	other	https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/blob/main/LICENSE.md	flux-1-dev-non-commercial-license	text-to-image SVDQuant FLUX.1-Krea-dev FLUX.1 Diffusion Quantization ICLR2025	text-to-image-synthesis

Model Card for nunchaku-flux.1-krea-dev

This repository contains Nunchaku-quantized versions of FLUX.1-Krea-dev, designed to generate high-quality images from text prompts. It is optimized for efficient inference while maintaining minimal loss in performance.

Model Details

Model Description

• Developed by: Nunchaku Team
• Model type: text-to-image
• License: flux-1-krea-dev-non-commercial-license
• Quantized from model: FLUX.1-Krea-dev

Model Files

• svdq-int4_r32-flux.1-krea-dev.safetensors: SVDQuant quantized INT4 FLUX.1-Krea-dev model. For users with non-Blackwell GPUs (pre-50-series).
• svdq-fp4_r32-flux.1-krea-dev.safetensors: SVDQuant quantized NVFP4 FLUX.1-Krea-dev model. For users with Blackwell GPUs (50-series).

Model Sources

• Inference Engine: nunchaku
• Quantization Library: deepcompressor
• Paper: SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
• Demo: svdquant.mit.edu

Usage

• Diffusers Usage: See flux.1-krea-dev.py. Just replace the safetensors with the ones from this repository. Check our tutorial for more advanced usage.
• ComfyUI Usage: See nunchaku-flux.1-dev.json. Just replace the safetensors with the ones from this repository.

Performance

Citation

@inproceedings{
  li2024svdquant,
  title={SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models},
  author={Li*, Muyang and Lin*, Yujun and Zhang*, Zhekai and Cai, Tianle and Li, Xiuyu and Guo, Junxian and Xie, Enze and Meng, Chenlin and Zhu, Jun-Yan and Han, Song},
  booktitle={The Thirteenth International Conference on Learning Representations},
  year={2025}
}

Attribution Notice

The FLUX.1 [dev] Model is licensed by Black Forest Labs Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs Inc. IN NO EVENT SHALL BLACK FOREST LABS INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.