An XML-RPC server that exposes a GPU-accelerated colorization pipeline for black-and-white images and video frames. Built on top of the [Nunchaku](https://github.com/mit-han-lab/nunchaku) SVDQuant FP4/INT4 transformer and the `Qwen-Image-Edit-2511` diffusion model.
Related
divelab/LIFT: [ICML 2026] Code implementation of Learnability-Informed Fine-Tuning of Diffusion Language Models
[ICML 2026] Code implementation of Learnability-Informed Fine-Tuning of Diffusion Language Models
sanjanaprasath01-hue/handwritten-digit-recognition-cnn: A deep learning project to recognize handwritten digits using CNN
A deep learning project to recognize handwritten digits using CNN
Qirui-jiao/DetailMaster: Official repo for DetailMaster: Can Your Text-to-Image Model Handle Long Prompts? [ICML2026]
Official repo for DetailMaster: Can Your Text-to-Image Model Handle Long Prompts? [ICML2026]