Xinjian Zhang

Results 2 issues of Xinjian Zhang

Thx for ur work. It is very hard to follow if there no evaluation code ~

Thanks for ur effort for diffusion model. I want to know why we need to rebuild a vae in inference stage. I think it will introduce extra GPU cost. https://github.com/huggingface/diffusers/blob/a85b34e7fdc0a5fceb11aa0fa6199bd9afaca396/examples/text_to_image/train_text_to_image_sdxl.py#L1217C16-L1223C24