Olive VS SDAtom-WebUi-us

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

Not sure because I'm using the vladmandic fork (https://github.com/vladmandic/automatic) that recently got a queueing feature. You could check out this one but I didn't try it myself: https://github.com/Kryptortio/SDAtom-WebUi-us

I found this, but cant seem to get it to work. SDAtom-WebUi

I installed this extension for Automatic1111 a while back: https://github.com/Kryptortio/SDAtom-WebUi-us. It isn't on the extensions folder and doesn't appear on the extensions tab. How do I remove it?

Even better? queue for A1111, https://github.com/Kryptortio/SDAtom-WebUi-us Each task can have different negative prompt and settings (resolution, hires. Fix, CFG, etc), can add more tasks on the fly, can save queue list to continue later.

If you run into some issues here is some troubleshooting help. If that doesn't help you can report bugs here.

Haha a pretty massive project for sure! Sounds like it would be absolutely awsome in the end though. A tool that I found useful was: https://github.com/Kryptortio/SDAtom-WebUi-us it lets you set up a queue of your different prompts and it'll process them one by one. I basically put in my different prompts, and generated a batch of 5 for each one, then chose the best at the end. You could do something similar for your deck potentially? ... Also, you got a decklist for the deck your describing, wouldn't mind having a gander ;)

Check if you have the latest version, I think I fixed a big bug for i2i this morning.