Closed nbren12 closed 6 months ago
cc @mnabian
Yair made a PR here to fix this: https://github.com/NVIDIA/modulus/pull/373 There were some issues reported by Tao, and we ended up reverting this PR here: https://github.com/NVIDIA/modulus/pull/396
@mnabian this is a separate issue that only effects inference.
BTW, I also had a PR on the conditional scaling: https://github.com/NVIDIA/modulus/pull/381
I think there is a similar bug to #229 in the sampler:
https://github.com/NVIDIA/modulus/blob/9b0b7cc71fb280c028e09ee56726c0caa387c63b/modulus/utils/generative/sampler.py#L188
x_lr should not be scaled by "s". It is not part of the evolved diffusion process, it is a conditional input.