Open RunDevelopment opened 1 month ago
Do you want help fixing the inference tests?
Sure, that would be nice. My main issue is that I don't know how LUD-VAE is supposed to be used and didn't have the time to look into that yet. Does our image -> image call API even make sense for LUD-VAE?
I'm not really sure what LUD-VAE even is. Skimming the repo made it seem like a denoiser
It's the opposite: it adds noise. The arch is supposed to learn the noise of some input images to generated noisy datasets for training models.
Interesting. Well if it's just clean -> noisy then our call API should work fine, no?
I saw some stuff suggesting that LUD-VAE is parameterized at inference time, so I'm not sure where image -> image will work. But again, I haven't looked into it yet.
We might have to make a new model descriptor type for this
Not sure if this will be useful for spandrel to support. Inference tests don't work yet, but detection and loading does.