Kolors KeTu large model series workflow

Run workflows online!

Kolors is a large-scale text-to-image generation model based on potential diffusion developed by the Kuaishou Kolors team. After training on billions of text-image pairs, Kolors shows significant advantages over open-source and proprietary models in terms of visual quality, accurate complex semantics, and text rendering of Chinese and English characters. Additionally, Kolors supports both Chinese and English inputs and performs well in understanding and generating specific Chinese content.

Local Deployment:

ComfyUi node plugin installation: https://github.com/kijai/ComfyUI-KwaiKolorsWrapper

Kolors model download: https://hf-mirror.com/Kwai-Kolors/Kolors/tree/main

Download to folder: ./ComfyUI/models/diffusers/Kolors.

Download the following files and the scheduler and text_encoder folders.

├───/scheduler/
│       scheduler_config.json
│
├───/text_encoder/
│       config.json
│       pytorch_model-00001-of-00007.bin
│       pytorch_model-00002-of-00007.bin
│       pytorch_model-00003-of-00007.bin
│       pytorch_model-00004-of-00007.bin
│       pytorch_model-00005-of-00007.bin
│       pytorch_model-00006-of-00007.bin
│       pytorch_model-00007-of-00007.bin
│       pytorch_model.bin.index.json
│       tokenizer.model
│       tokenizer_config.json
│       vocab.txt
│
└ config.json
  diffusion_pytorch_model.fp16.safetensors

Use the sdxl vae file.