LinFusion
LinFusion copied to clipboard
Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"
Is the dataset a subset of [laion/aesthetics_v2_4.75](https://huggingface.co/datasets/laion/aesthetics_v2_4.75)? Or, do you have the original path name of each sample?
Thank you for your exceptional work! Your paper mentioned the distillation training process on SD-v1.5: "Training is conducted on 8 RTX6000Ada GPUs with a total batch size of 96 under...
If there's flux support, it will give ultra high quality images
will support flux? We really hope to open source support for flux acceleration,
Thanks for your awesome work. I'm trying to reproduce your results for distilling SD-XL. I ran `bash examples/train/distill_xl.sh` on an 8 - GPU machine. It has been running normally for...
Thank you for great work! when I tested the time cost of linfusion and the dreamshape-v8-base model, I found that linfusion took an average of **1.8s** on A100, but the...