Image-to-Image
Diffusers
Safetensors
old-photo-colorization
image-colorization
flux
cvpr-2026
unofficial
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("LuckyCookie114/colorflux", dtype=torch.bfloat16, device_map="cuda")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]ColorFLUX Weights
This repository hosts weights for an unofficial implementation of:
ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization
CVPR 2026 Highlight
Important Notice
This is not the official release from the paper authors. This repository is not affiliated with, endorsed by, or maintained by the original paper authors or their institutions.
These weights are provided for academic research purposes only. Commercial use is strictly prohibited, including but not limited to commercial products, paid services, business integration, advertising, or monetized deployment.
Citation
@inproceedings{li2026colorflux,
title = {ColorFLUX: A Structure-Color Decoupling Framework for Old Photo Colorization},
author = {Li, Bingchen and Wang, Zhixin and Li, Fan and Xu, Jiaqi and Guo, Jiaming and Pei, Renjing and Li, Xin and Chen, Zhibo},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2026}
}
- Downloads last month
- 17