guided-diffusion
guided-diffusion copied to clipboard
Unconditional Sampling from Conditional Model
Any suggestions for how to achieve this? Working on CLIP guided generation and would like to try with 512x512.
This is unofficial, but some people have found it possible to achieve this by randomizing the class label at every timestep. Example: https://twitter.com/RiversHaveWings/status/1423034386354561024