The community wanted to know what it was costing me, so I dug into it a bit and have a fairly "literal" answer to that question (generally). I run a custom Stable Diffusion bot for a small community that has generated many tens of thousands of images. If you want to help out, please feel free to open an issue or pull request. I see a few bits of feedback here about issues with the Scribble Diffusion UI, and I'm tracking them on the GitHub repo. There are already a bunch of models on Replicate that build on it. It also allows for controlling Stable Diffusion using other inputs like pose estimation, edge detection, and depth maps.ĬontrolNet has only existed for three weeks, but people are already doing all kinds of cool stuff with it, like an app that lets you pose a stick figure and generate DreamBooth images that match the pose. This is all built on ControlNet, a brilliant technique by Lvmin Zhang and Maneesh Agrawala for conditioning diffusion models on additional sources, in this case human scribbles. We built Scribble Diffusion as an open-source app to demonstrate how to use Replicate. I'm an engineer at Replicate, which is a place to run ML models in the cloud. I love seeing all these links to your scribbles. (EDIT: even if you aren’t using the A1111 WebUI, this repo has a nice set of examples of what each of the ControlNet models does, so it may be worth checking out.) home repo: but for WebUI you probably want the ones linked from the readme of the WebUI ControlNet extensions Should work in any current browser, and at least the A1111 UI, with ControlNet models, works on machines with as little as 4GB VRAM. Which is not to be dismissive, its a very nice demo of what SD+ControlNet scribble can do.īut for people who like it, the ControlNet scribble model (and the other ControlNet models, depth-map based, pose control, edge detection, etc.) are supported in the ControlNet extension to the A1111 Stable Diffusion Web UI, and probably similar extensions for other popular stable diffusion UIs. This looks like its just a quick front-end to the ControlNet scribble model (perhaps with a customized underlying model instead of base Stable Diffusion), with canned settings, presumable a canned negative prompt, and maybe some common stuff added beyond the user input to the positive prompt.
0 kommentar(er)
