Stories by chengzeyi

VACE: An all-in-one model designed for video creation and editing

WaveSpeedAI: Bring the Fastest AI Video and Image Generation to the World

Fastest HunyuanVideo Inference with Context Parallelism and First Block Cache

ParaAttention: Speed Up Flux and Mochi Inference with Multiple GPUs

Stable-fast for SD inference: Faster than AITemplate, On par with TensorRT

Stable Fast: Lightweight Inference Optimization Library for Stable Diffusion