huggingface / diffusion-fast

Faster generation with text-to-image diffusion models.

https://pytorch.org/blog/accelerating-generative-ai-3/

huggingface/diffusion-fast Issues

CUDA generator expects graph capture to be underway, but the current stream is not capturing
Closed 4 months ago3
lora support for optimization
Closed 4 months ago3
quantization issue for weight only int8 with fp16
Closed 6 months ago1