open-pose-editor
sd-scripts
open-pose-editor | sd-scripts | |
---|---|---|
12 | 64 | |
708 | 4,222 | |
- | - | |
4.8 | 9.7 | |
3 months ago | 7 days ago | |
TypeScript | Python | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
open-pose-editor
-
Do anyone knows how to create such Character like this ?
you can do it here or just use openpose module alone in controlnet with a given image
-
woman sitting on a bed
You can try this : https://zhuyu1997.github.io/open-pose-editor/
-
Fixing background inconsistencies.
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?
-
ControlNet 1.1 fingers...
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.
- ControlNet-v1-1-nightly: Controlnet 1.1 is coming to Automatic with a lot of new new features
-
Hope you will like it~
https://zhuyu1997.github.io/open-pose-editor/ set background image and make openpose matchstick man
-
Can someone integrate Magic Poser Web + Open Pose Editor?
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/
-
Simple way of posing in ControlNet?
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/
-
3D-Open-Pose-Editor ported to A1111 Extension (Not yet on the in app list of extensions / Link in comments)
Web version: https://zhuyu1997.github.io/open-pose-editor/ (Exports Canny/Depth/Normal/Edge model images to PNG for import).
- [Git/HTTP] - Perhaps the best Open Pose Editor - includes hands/finger manipulation and saves PNGs for Openpose/Depth/Normal and Edge models.
sd-scripts
- Everything you know about loss is a lie
- Evidence that LoRA extraction in Kohya is broken?
- Stable Diffusion XL (SDXL) DreamBooth training with EMA (Exponential Moving Average) on the way
-
Installing kohya_ss GUI on AWS
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.
- Question on SD Finetuning
-
Trying to put up a simple dreambooth for sdxl, but an errors pops up
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 "
-
Finally SDXL coming to the Automatic1111 Web UI
You can try and test training LoRAs now https://github.com/kohya-ss/sd-scripts/tree/sdxl
-
Help with LORA Training - Kohya_ss Regularization
This might help.
-
need a lora traning guide for linux
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.
-
SDXL 0.9 is wild but trying to imagine where we go from here is breaking my brain.
"Direct training" is already feasible with masking in kohya-ss: https://github.com/kohya-ss/sd-scripts/pull/589
What are some alternatives?
openpose-editor - Openpose Editor for AUTOMATIC1111's stable-diffusion-webui
kohya_ss
sd-webui-controlnet - WebUI extension for ControlNet
sd_dreambooth_extension
sd-webui-3d-open-pose-editor - 3d openpose editor for stable diffusion and controlnet
ComfyUI - The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
ChatGPT-Next-Web - A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。
bitsandbytes-rocm
octoart - Generate beautiful GitHub Octocat art with one click
lora - Using Low-rank adaptation to quickly fine-tune diffusion models.
ControlNet-v1-1-nightly - Nightly release of ControlNet 1.1
kohya-trainer - Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning