ThisisBillhe

tiny-stable-diffusion. Tiny optimized Stable-diffusion that can run on GPUs with just 1GB of VRAM. (Beta)

EfficientDM. [ICLR 2024 Spotlight] This is the official PyTorch implementation of "EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models"

NAR. [ICCV 2025] The official implementation of "Neighboring Autoregressive Modeling for Efficient Visual Generation"

ZipAR. [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality"

ZipCache. [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

torch_quantizer. torch_quantizer is a out-of-box quantization tool for PyTorch models on CUDA backend, specially optimized for Diffusion Models.

BiViT. The official implementation of BiViT: Extremely Compressed Binary Vision Transformers

Speculative-Jacobi-Decoding. Custom implementation of paper "Speculative Jacobi Decoding" on Lumina-mGPT