search

cswry / SeeSR

[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
Apache License 2.0
390 stars 25 forks source link

What's the difference between from_pretrained_orig() and from_pretrained()? Blurry turbo output? #49

Open octopushugger opened 4 months ago

octopushugger commented 4 months ago

I get this error when trying to use from_pretrained_orig():

File "C:\Stuff\Apps\SeeSR\gradio_seesr_turbo.py", line 48, in <module> unet = UNet2DConditionModel.from_pretrained_orig(seesr_model_path, subfolder="unet") TypeError: UNet2DConditionModel.from_pretrained_orig() missing 1 required positional argument: 'seesr_model_path'

Changed it to from_pretrained() and it appears to work fine, however the turbo output is blurrier than I would have expected. https://imgsli.com/MjY3ODY4/0/1

Is the blurriness just the nature of the turbo model or is it because I'm loading something wrong?

octopushugger commented 4 months ago

Or did something get pushed to the repo that wasn't intended? The code doesn't match up with the readme. Like the code is requesting models from SD2.1 but the readme says use 2.0. Also the UNET from sd-turbo doesn't appear to be used at all.