open-pose-editor VS sd-scripts

you can do it here or just use openpose module alone in controlnet with a given image

You can try this : https://zhuyu1997.github.io/open-pose-editor/

It won't need a processor unless you're using an input photograph that matches the composition you want. For the mlsd input, maybe try draw two horizontal white lines on a black canvas, for where you want the floor and ceiling meet the walls, and play with the strength. There's also tools like https://zhuyu1997.github.io/open-pose-editor/ and https://app.posemy.art/ and various extensions. I know you said "without resorting to creating a background"... just google some gym photographs?

You can also try looking at https://zhuyu1997.github.io/open-pose-editor/Web based (May also have a extension) but it does have fingers and will give you a Pose, Depth, Normal and canny image.

https://zhuyu1997.github.io/open-pose-editor/ set background image and make openpose matchstick man

Open Pose Editor is great but doesn't have better IK functionality of Magic Poser even though its hands and feet have IK. https://zhuyu1997.github.io/open-pose-editor/

Yeah that could also work, but some more complicated poses are tough :) I saw that this one are quite good: https://zhuyu1997.github.io/open-pose-editor/

Web version: https://zhuyu1997.github.io/open-pose-editor/ (Exports Canny/Depth/Normal/Edge model images to PNG for import).

This repository mostly provides a Windows-focused Gradio GUI for Kohya's Stable Diffusion trainers... but support for Linux OS is also provided through community contributions.

Leaving this here because i'm very tired, so this is the file of the ipynb that uses the sdxl_train.py from the https://github.com/kohya-ss/sd-scripts/tree/sdxl repo, if anybody find out why when getting to the training i get this very empty error : " [00:09:11] WARNING The following values were not passed to "

You can try and test training LoRAs now https://github.com/kohya-ss/sd-scripts/tree/sdxl

This might help.

Kohya_ss sd-scripts Seems to be the standard for lora training. The linked page has an English translation, but doesn't really have system specific tips. Someone else has a popular gui for it, but it's designed with windows in mind. There's another, simpler gui, but its still in development and the dev doesn't do any testing on Linux. With any of these, I run into dependency conflicts like crazy.

"Direct training" is already feasible with masking in kohya-ss: https://github.com/kohya-ss/sd-scripts/pull/589