Open aneesurhashmi opened 8 months ago
@aneesurhashmi Hi, I encountered the same problem, did you solve it?
Hi @yihp, no, I was not able to solve it and decided to switch to the stable diffusion pipeline. You can have a look at my implementation here https://github.com/BioMedIA-MBZUAI/XReal
Hi, Thank you for the amazing work!
I tried training a model using your code with the DDPM scheduler, which works fine during the interference/sampling as well. However, I am not able to use the DDIM scheduler for inference. The model outputs a completely blurred image with DDIM, even with 1000 steps. Do you have any idea what could be the problem here?