multidiffusion-upscaler-for-automatic1111 VS a8r8

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.

Created using A8R8:

I used A8R8, activated Tiled Diffusion with a scale of 2 and Ultrasharp Upscaler with CN Tile with a 0.35 denoising strength and a 4.5 CFG

Try https://github.com/ramyma/a8r8/, it's a completely different UI that focuses on being minimalistic and open.

It's an opensource interface that works with existing A1111 installations, it has many features including upcaling, Contolnet support, inpatinting/outpainting. The link is in the post, it's https://github.com/ramyma/a8r8

Feel free to drop-in suggestions and feedback on https://github.com/ramyma/a8r8/discussions, or even through direct messages.