Mengfan Shi

Major in computer vision

Results 2 comments of


                                            Mengfan Shi

use_gradient_checkpointing_offload occupies more VRAM when train i2v model

Yes, that's the problem. Adding it makes it normal. Thank you very much.

Notable gap between image stylization and video stylization based on animatediff and controlnet

Thanks a lot for your suggestion ! I'll try to train a lora on all attentions layers.