T2I-Adapter VS sd-webui-controlnet

I've found some documentation here https://github.com/TencentARC/T2I-Adapter/blob/SD/docs/coadapter.md

Yeah, if you have a high res image, you can get color info at super low-res and then regenerate the colors at high res with another model. (though this isn't an efficient approach at all)

https://github.com/TencentARC/T2I-Adapter

i've also seen a controlnet do this.

https://github.com/TencentARC/T2I-Adapter

It works with the Mikubill ControlNet plugin for A1111.

These are from Tencent: https://github.com/TencentARC/T2I-Adapter

I think they're for T2I-adapter models, which can be downloaded here.

Apart from Controlnet, T2I Adapter works quite well for this. https://github.com/TencentARC/T2I-Adapter

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