multidiffusion-upscaler-for-automatic1111 VS sd-webui-controlnet

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.

A crucial step for achieving stable diffusion controlnet settings is the installation of the controlnet extension in Google Colab. Whether on a Windows PC or Mac, installing controlnet is vital for stable diffusion of human pose details. Additionally, updating the controlnet extension is necessary to maintain stability and achieve the desired results in OpenPose model. To install the v1.1 controlnet extension, go to the “extensions” tab and install it from this URL: https://github.com/Mikubill/sd-webui-controlnet. If you already have v1 controlnets installed, delete the folder from stable-diffusion-webui/extensions/. Install the v1.

1.1.420 Image-wise ControlNet and StyleAlign

I opened a request thread on ControlNet GitHub you can give a support : https://github.com/Mikubill/sd-webui-controlnet/issues/2319

It has been possible for 7 months now

I sometimes use a very similar technique in Cinema4d (here is a link to a c4d file with preset materials referencing proper colors for Semantic Segmentation if any other c4d user wants to try it), but yours is a much more accessible solution as it's free and it's accessible online.

There are models available that give you more control - in some senses, at least.

For example, you can use Stable Diffusion with 'ControlNet' [1] where for example, you can input an 'openpose' to choose the pose of people in the scene.

There's also a 'Regional Prompter' [2] which lets you use different prompts for different areas of the image, giving you some control over the composition.

You can also use 'inpainting' to regenerate select parts of your image if, for example, you don't like the shape of the clouds.

Of course this stuff isn't perfect - for example, you'll get hands with the wrong number of fingers sometimes, no matter what you specify :)

[1] https://github.com/Mikubill/sd-webui-controlnet