a1111-sd-webui-locon VS Olive

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

I use Microsoft Olive to optimize my networks. It works rather well as I did make my inference speed like 2-3 times faster, the models smaller and VRAM usage was reduced as well, though this needs the latest nvidia drivers to happen.

First update drivers, then follow the instruction here: Olive/README.md at main · microsoft/Olive · GitHub I try SD1.5 and DreamShaper model, both hit 30it/s

Microsoft has provided a path in DirectML for vendors like AMD to enable optimizations called ‘metacommands’. In the case of Stable Diffusion with the Olive pipeline, AMD is building driver support for a metacommand implementation intended to improve performance and reduce the time it takes to generate output from the model. This feature will be validated on AMD RDNA™ 3 devices including AMD Radeon™ RX 7900 Series graphics cards and AMD Ryzen™ 7040 Series Mobile processors with Radeon™ graphics.

Olive is an easy-to-use hardware-aware model optimization tool that composes industry-leading techniques across model compression, optimization, and compilation. Given a model and targeted hardware, Olive composes the best suitable optimization techniques to output the most efficient model(s) for inferencing on cloud or edge, while taking a set of constraints such as accuracy and latency into consideration.

Repository: https://github.com/microsoft/Olive