wcde
wcde
Looks like SwinIR x2 is not working now. I get this in any model: ``` File "...\modules\images.py", line 286, in resize_image res = resize(im, width, height) File "...\modules\images.py", line 278,...
In code hardcoded scale to 4. Should be something like that: ``` img = upscaler_utils.upscale_2( img, model, tile_size=shared.opts.SWIN_tile, tile_overlap=shared.opts.SWIN_tile_overlap, scale=model.scale, desc="SwinIR", ) ``` Second problem - model is loaded with...
It looks pretty much useless. For decoding 1024x1024 it consumes 26 GB VRAM and its 10+ times slower than regular VAE. In ClosedAI examples they even use 256x256... At least...
@zhengkw18 can you provide some code examples how compute EMS?
@dxqbYD I think what you're talking about is only valid for unknown things. For example, if we're training a specific person, then we naturally want to give the model his...
Another way to “make mutants faster”...
I implemented it as extension, it works with 1.5 too. https://github.com/wcde/sd-webui-kohya-hiresfix
@AndreyRGW just set resolution whatever you want and generate with enabled extension. 
You should install it from git, try this: ```pip install -e "git+https://github.com/deepinsight/insightface.git#egg=insightface&subdirectory=python-package"```