a1111-sd-webui-locon VS unpaint

Workaround in the bottom of this thread: https://github.com/KohakuBlueleaf/a1111-sd-webui-locon/issues/40

And are you sure they're not Loha or LoCON instead of LoRA? Try Additional Networks, but you may need this extension instead/as well. I ended up having to delete Additional Networks because it was causing problems. I don't know if it's fixed.

Click the green button on the github page for the extension and in the pop-up click on the little icon that looks like two squares overlapping to copy the link.

I installed the webui locon from here:https://github.com/KohakuBlueleaf/a1111-sd-webui-locon/blob/main/scripts/main.py

Auto1111 has integrated the Locon version of LoRA to its built in extensions. Meaning that the KohakuBlueleaf extension is in conflict with the built in LoRA extension and must be removed. I tested this and my render came out just as expected with a LoRA applied.

They seem to use this extension , but I can't figure out what is even different about it. Does anyone know?

Also earlier I received failed to match lora keys error or something like that and I had to install this extension to make it go away. The output is different when there's an error like this. https://github.com/KohakuBlueleaf/a1111-sd-webui-locon

Here are the details: Running Unpaint on the Xbox Series consoles · axodox/unpaint Wiki (github.com)

I also started to build an app of my own on top of it called Unpaint (which you can download and try following the link), targeting Windows and (for now) DirectML. The app provides the basic Stable Diffusion pipelines - it can do txt2img, img2img and inpainting, it also implements some advanced prompting features (attention, scheduling) and the safety checker. It is lightweight and starts up quickly, and it is just ~2.5GB with a model, so you can easily put it on your fastest drive. Performance wise with single images is on par for me with CUDA and Automatic1111 with a 3080 Ti, but it seems to use more VRAM at higher batch counts, however this is a good start in my opinion. It also has an integrated model manager powered by Hugging Face - though for now I restricted it to avoid vandalism, however you can still convert existing models and install them offline (I will make a guide soon). And as you can see on the above images: it also has a simple but nice user interface.

The source code is on GitHub (here: axodox/native-diffusion (github.com)), there is also an installer in releases, if you want to try it.

I made a C++ test project here: Release Olive Test · axodox/native-diffusion (github.com)

Well, I am working on a port of StableDiffusion which uses C++ only, no python, no other dependencies and crap. I have txt2img, img2img and inpainting fully working now.