Wan: Open and Advanced Large-Scale Video Generative Models

PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

flux distillation and stuff

2-4x faster ComfyUI Image Upscaling using Tensorrt ⚡

Official repository for LTX-Video

Slice regions of the canvas and convert them to masks for regional conditions widh PNG preview output. And a few support nodes.

Compositor Node experiments

A powerful node suite for ComfyUI that streamlines your workflow. It offers smart prompt management, image metadata analysis, visual comparison tools, customizable templates, history tracking, and …