multidiffusion-upscaler-for-automatic1111 VS automatic

Use tiled VAE, it will save VRAM: pkuliyi2015/multidiffusion-upscaler-for-automatic1111: Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0 (github.com)

My favorite solution is to not use ultimate Sd upscale and instead use multidiffusion-upscaler.

sure, i personally use 'tiled diffusion' https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111, works like charm also use adetailer for faces if its needed.

What worked for my 1080 was using TiledVAE and turning down the quality of my previews - I don't pay much attention to it/s but it's definitely faster than using --medvram, and now I can handle batches and large resolutions without things exploding on me.

I would highly recommend adding https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 to your A1111 installation, TiledVAE is enabled automatically under the hood in A8R8; this will allow you to get even larger generations before getting an out of memory error. You'll get a Tiled Diffusion checkbox with some reasonable hardcoded defaults as well.

Use Tiled VAE https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111

That's weird. 10GB should allow you to hires to 2048x2048 at least. Use Tiled VAE extension https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 that will allow you to go even beyond that.

> it won't ever be a viable option

For production workloads, I generally agree. It's an unsupported hack with a questionable future, I wouldn't do anything money-making with it.

However, for tinkering and consumer workloads, it already works pretty well. Enough of cuDNN and cuBLAS work to run PyTorch and in turn, Stable Diffusion with https://github.com/lshqqytiger/ZLUDA - there's even a fairly user-friendly setup process already in https://github.com/vladmandic/automatic .

I was able to get a personal non-ML related project working on my AMD card in just a few minutes, which saved me a lot of development time before I then deployed the production workload on NV hardware (this is probably why AMD pulled the plug on the project - it's almost more of a boost to NV than anything else, AMD really need people to be writing code on ROCm to deploy on AMD datacenter hardware).

While I currently use SD.Next[1], I have tested ComfyUI locally with my AMD card. The UI can be daunting, but you learn quite a great deal about how a Stable Diffusion pipeline works. In addition some innovations and advances find their way into ComfyUI first.

[1] https://github.com/vladmandic/automatic

I used SD.NEXT ( https://github.com/vladmandic/automatic ) and https://civitai.com/models/82098/add-more-details-detail-enhancer-tweaker-lora and epicphotogasm_lastUnicorn

I found this thread on GitHub talking about how this was fixed in the latest version with an optional setting. I tried enabling it, as they mentioned, but it just resulted in an immediate CUDA out of memory error when starting generation. So it seems I'm actually needing the shared memory, which I assume is my issue.

As always, do check out our more detailed changelog, give us a quick install from our Repo, and stop by our Discord Server for any questions or help you may need.

SD.Next

Today I finally wanted to give SDXL a chance, so I set everythin up according to Vladmandic's Wiki https://github.com/vladmandic/automatic/wiki/SD-XL

I'm trying to get SDXL working on Vlad's SDNext, but I keep getting the error in the title when trying to run basic operations. I'm not sure what's going on, I followed his guide for it to a T.

We used an inference container based on SDNext, along with a custom worker written in Typescript that implemented the job processing pipeline. The worker used HTTP to communicate with both the SDNext container and with our batch framework.