Diffusers?
#9
by
tintwotin
- opened
How can the RTX 4090 friendly version be run via Diffusers?
I did see this: FastVideo/FastHunyuan-diffusers
For inference, we can inference FastHunyuan on single RTX4090. We now support NF4 and LLM-INT8 quantized inference using BitsAndBytes for FastHunyuan. With NF4 quantization, inference can be performed on a single RTX 4090 GPU, requiring just 20GB of VRAM.
Are there any code examples to showcase how to do this?
Please see our github repo.
https://github.com/hao-ai-lab/FastVideo