multidiffusion-upscaler-for-automatic1111 VS ComfyUI_TiledKSampler

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.

Give my tiled sampler nodes a try. padded mode works quite nicely for the refiner.

I haven't used it but check this out: https://github.com/BlenderNeko/ComfyUI_TiledKSampler

That's a natural consequence of tiled samplers having a limited field of view. None of the tiles ever get to see multiple water surfaces so from their perspective everything is a-okay. This can get really trippy when you don't use these samplers for denoising but for text to image. I could have helped it by giving it more hints in the form of control nets, but that wasn't really the point here.