RootOnChair

Data-free 4-bit quantization of diffusion transformers with Nunchaku Lite SVDQuant: nvfp4 works out of the box, and a Hadamard rotation brings int4 up to nvfp4 quality on A100-class GPUs. [Read More]

Consistency Models is a popular approach to reduce Stable Diffusion required steps from 30-50 steps to 1-8 steps without sacrifices much of quality image. In reality, you can easily apply Consistency Models to any community base models by attach a LoRA to the model, without any retraining. However, when deep... [Read More]