EfourC

> Now scaling to 3x LDSR (1536x3048) works. It's not fast, but it works! 😊 Again... Thanks for posting! > I wish I know why upscaling is so slow. It...

The details are a little ambiguous.. I agree with Xyem about what is seems like, but you'll have to do a bit more investigation. Changing a setting like that should...

Furthermore, make sure that ControlNet is not enabled in the txt2img / img2img tabs. Maybe a possible theory to explain your poor image quality: If you have ControlNet enabled for...

I'm running into a really strange problem. Any advice of how I should narrow down the root cause? **_Edit:_** Oops, forgot to say my startup arguments: `--xformers --opt-channelslast --no-half-vae` I...

With that commit, and the current master, the problem doesn't happen -- I only see it after everything is upgraded for Torch2. Behavior Ok:  

I did some more permutations of testing, especially to see if `--opt-sdp-attention` instead of xformers made a difference with the Torch 2 venv. What I found out is that the...

This is nice, though it's a bit too busy on the printouts during startup (I would personally still use it with no changes rather than not have it, however!).

I was thinking about this a little more while learning about tqdm and realized that since the startup logs will be copy/pasted into countless threads (not to mention everyone will...

Nice work! Just tried and works well, so naturally disregard my previous post considering your latest changes, totally mooted;)

Hit an error when I tried to toggle close the extra networks display: Error printout ```Traceback (most recent call last): File "N:\stable-diffusion-webui\venv\lib\site-packages\gradio\routes.py", line 337, in run_predict output = await app.get_blocks().process_api(...