sd-webui-3d-open-pose-editor VS sd-webui-controlnet

I'm having trouble creating a charactersheet for a Lora. I found that really good tutorial (https://cobaltexplorer.com/2023/06/character-sheets-for-stable-diffusion/) that basicically goes the way of creating a charactersheet with multiple views in combination with open pose. Trying that out and experimenting a bit it came apearent, that my hardware is not really capable of rendering the full charactersheet-image and what came out looked not pretty. So I figured I could take the initial openpose-modelimage for the charactersheet, break it into it's sections and let them be generated piece by piece. And that is when the trouble began. I was able to create a good prompt with a good seed to get a nice frontal image for the character (we're talking realistic photography, not anime). But as soon as I applied the according controlnet-part for the frontal-image it messed up the face completely to look completely different - even after keeping the prompt, the seed and everything else the same. In the end I figured out that some of the lines in the controlnet-image (I did not use the "face" one there) seem to mess with the face. So I made a controllnet-image from the straight frontal image and that seems to work great now and creates reproduceable images. Now I need to rotate said openpose-image to get sideviews and backviews, but I can't find a way to do this. I have tried to work with OpenPose3D-Editor (https://github.com/nonnonstop/sd-webui-3d-open-pose-editor) but that thing needs a whole body - I only have a facialimage. In the end those openpose-models are jsonfiles, maybe that can be an approach, but I reached a dead end here.

This is also how I started out, but as other commenters wrote, it really depends too much on luck. I switched to using this extension: https://github.com/nonnonstop/sd-webui-3d-open-pose-editor

I used cn-openpose and softedge heavily to get the character to pose. I used this extension for most of the images https://github.com/nonnonstop/sd-webui-3d-open-pose-editor. All of the pose were grabbed by using stock images as reference and then manually positioned.

Regarding the zoom and poses, ControlNET can help you. There are some websites with poses for that extension: https://openposes.com/ And this extension can help you: https://github.com/nonnonstop/sd-webui-3d-open-pose-editor

The Automatic1111 Web UI has 3D Open Pose Editor extension [github]. TBH at first I felt like the process on the video was a lot faster than in Web UI, but then I realized the video is sped up.

There is one already https://github.com/nonnonstop/sd-webui-3d-open-pose-editor

I had been using the [3D Openpose editor](https://github.com/nonnonstop/sd-webui-3d-open-pose-editor) and was hoping Controlnet would interpret the different thicknesses of the connectors as depth but unfortunately that doesn't seem to be the case. I should have phrased the title better because what I'm really looking for is a skeleton that can be posed that also communicates depth, hopefully something comes down the pipeline one day

Extension It is also available as "3D Openpose Editor" in the install extensions tab. Maybe Suitable

I just installed 3D Openpose from https://github.com/nonnonstop/sd-webui-3d-open-pose-editor The editor is working well. After clicking on "Makes Images" , I can see images on the "Send to ControlNet" tab. But when I clicked on "Send to txt/img2img" nothing happened. What have I done wrong?

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