It's not SDXL, it's Kolors! (and yes, it's alreay in ComfyUI). Fantastic new model.
/ quick_eyed_sky (to support, get prompts, ideas, and images)
Erratum at 1:56, the images are more like 30 steps/5 cfg.
https://github.com/Kwai-Kolors/Kolors...
The colab is here: https://colab.research.google.com/dri...
From their Github: Kolors is a large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team. Trained on billions of text-image pairs, Kolors exhibits significant advantages over open-source and closed-source models in visual quality, complex semantic accuracy, and text rendering for Chinese and English characters. Furthermore, Kolors supports Chinese and English inputs, demonstrating strong performance in understanding and generating Chinese-specific content.
Playlist of AI tutorials: • Tutorials for Disco Diffusion (and other AIs) if you want to make your own images.
Some of my music you hear on my clips: / user-894673824