MultiDiffusion
MultiDiffusion copied to clipboard
omerbt
Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)
Hello. I ran into a problem, can anyone help me on this. Here's the code I run ``` device = torch.device('cuda') sd = MultiDiffusion(device) mask = torch.zeros(2,1,512,512).cuda() mask[0,:,:256]=1 mask[1,:,256:]=1 fg_masks...
Why can't we just do non-overlapping generation without averaging? I presume you have tried and found that averaging gives better results. Is there any intuition or theory for that?
I want to use your evaluation dataset to test my method, can you release it? Thanks!!!
Hello!Thank you for your great work! But I have problem on formula derivation. I met difficulties when trying to derivatie equation 3 to equation 5.   Could you please...
Anyone can help ? The results I obtained are significantly different from those presented in the paper.
Interesting work, and I wonder when will codes for region-based generation release. BTW, the hugging face demo for region-based generation crashed, can you fix it? I really want to try...
Nice job! I wonder when will codes about how to train the ckpt release.
Since multidiffusion is just a diffusion process, did you ever compare it with different choices of schedulers and guidance scales? If you increase the guidance scale, can you get an...
in mult diffusion, some shceduler may not generate correct result。 which can fix the scheduler step view or tile in full latent. 部分采样器不支持，无法生成正确的图。本次PR增加了对各种采样器的支持，改进了算法~
