Due to Google's increasing policy of blocking Stable Diffusion and my own lack of time to continue making this project available on Google Colab, the project will be discontinued for maintenance.
However, you can also view the recommendations for some models in this repository and the collection of Prompts I maintained earlier.
How grateful I am to Google Colab for initially granting me the pleasure of experiencing the artistry of AI.
[Web UI] Go To Colab | [LoRA Train] Go To Colab | [Xformers Build] Go To Colab | Prompts Collection
Now the download script of "Recommended Loras" and "Recommended Checkpoints" has been built into the script (before startup), if you don't want to download it, you can disable them before startup.
Most of the models are the latest versions from CivitAI, but some LoRA models are marked with special versions, which are versions that I personally think are better. If you don't want to use this version, you may need to download other versions yourself (see below).
If you want to download other models, you can go to the CivitAI tab in WebUI to download it yourself (if you have checked the install Civitai Browser extension option). In addition, remember to check the Save to Additional Network option.
Warning: Please note that there may be legal risks before painting. Please note whether your painting may cause controversy and negative impact on the development of the AI community. Please use it with caution.
-
Paperspace Support(Not considered in the future) - Support for training LoRA Jupyter Notebook
- Optimize model download speed with aria2
- Internationalization
- Provide xformer support for Paperspace M4000 GPU
- Soft link LoRA in
models/Stable-diffusion
folder to Additional Network folder
Jupyter Notebook's Language is still Chinese, I want to find a way to make it internationalized, but maintaining two versions is a bit troublesome, so I will do it later.
Basic training script based on Akegarasu/lora-scripts which is based on kohya-ss/sd-scripts, but you can also use ddPn08/kohya-sd-scripts-webui which provides a GUI, it is more convenient, I also provide the corresponding SD WebUI extension installation method in stable_diffusion_1_5_webui.ipynb
.
Some models are not compatible with the training script, and the training script will not be able to train them. If you want to train them, you need to use the training script provided by the model author.
In kohya-ss/sd-scripts train_network documentaion, it notes that the cloneofsimo's repository and the d8ahazard's Dreambooth Extension for Stable-Diffusion-WebUI are not compatible at the current time. This is because they have extended some features.
It seems that the LoRA related to @kbr has disappeared, and I don't know the reason. Currently, you can find it at https://github.com/wibus-wee/stable_diffusion_chilloutmix_ipynb/releases/tag/koreanDollLikeness, I have uploaded it to the release.
In addition, I have updated the startup script so that if you check install
koreanDollLikeness
, it will be installed automatically.
(x1)
π St. Louis (Luxurious Wheels) (Azur Lane): https://civitai.com/models/6669/st-louis-luxurious-wheels-azur-lane(x1)
π Girls' Frontline-OTs-14"lightning": https://civitai.com/models/6525/girls-frontline-ots-14lightning(x0.5)
π @kbr/Korean Doll Likeness:https://civitai.com/models/7448/korean-doll-likeness( Has been re-uploaded to the release by me.)(x0.5)
π@kbr/Japanese Doll Likeness: https://civitai.com/models/10135(x0.5)
π@kbr/Taiwan Doll Likeness : https://civitai.com/models/7716/taiwan-doll-likeness(x0.5)
π Yae Miko | Realistic Genshin (Mixed): https://civitai.com/models/8484/yae-miko-or-realistic-genshin(x0.5)
π Gakki | Aragaki Yui | ζ°ε£η΅θ‘£: https://civitai.com/models/8416/gakki-or-aragaki-yui-or(x0.5 - x1)
π ChilloutMixss: https://civitai.com/models/10850/chilloutmixss(x0.5)
π Cute_girl_mix4: https://civitai.com/models/14171/cutegirlmix4(x0.5)
π Fashion Girl (v4.5): https://civitai.com/models/8217/fashion-girl(x0.5)
π RandomCoser: https://huggingface.co/AzureKn1ght/RandomCoser (backup?)
π - Very good, very recommended.
π - Good, recommended.
π - Good.
- [2.5D] ChilloutMix: https://civitai.com/models/6424/chilloutmix
- [2.5D] SunshineMix: https://civitai.com/models/9291/sunshinemix
- [2D] Grapefruit (hentai model): https://civitai.com/models/2583/grapefruit-hentai-model
- [2.5D] Chilled_re_generic_v2: https://drive.google.com/file/d/1KNU_giorZYOflT3gdwAPtIPh6sNE2oNR/view?usp=sharing (merged by wibus-wee, recipe by @sazyou_roukaku, recipe See here )
- [2D] Anything v4.5: https://huggingface.co/Airic/Anything-V4.5
- Ulzzang-6500 (Korean doll aesthetic): https://civitai.com/models/8109/ulzzang-6500-korean-doll-aesthetic
- Pure Eros Face: https://civitai.com/models/4514/pure-eros-face
Experimental LoRA refers to models that are not yet fully tested by me, and have not yet been determined to be compatible. If you want to use these models, please judge the compatibility with other LoRA by yourself.
- liuyifei: https://civitai.com/models/8453/liuyifei
- Lisa Blackpink: https://civitai.com/models/8605/lisa-blackpink
- Jisoo Blackpink: https://civitai.com/models/8311/jisoo-blackpink
- Rosè Blackpink: https://civitai.com/models/8600/rose-blackpink
- MoXin: https://civitai.com/models/12597/moxin
WebUI Jupyter Notebook built-in Extension, you can install it directly from the notebook.
- deforum-art/deforum-for-automatic1111-webui
- AlUlkesh/stable-diffusion-webui-images-browser
- camenduru/stable-diffusion-webui-huggingface
- camenduru/sd-civitai-browser
- camenduru/openpose-editor
- Mikubill/sd-webui-controlnet
- kohya-ss/sd-webui-additional-networks
- ddpn08/kohya-sd-scripts-webui (This extension has better install before WebUI Starting, otherwise you need to restart Application instead of just reload the UI.)
- d8ahazard/sd_dreambooth_extension
If you are using Google Colab, there are many precompiled wheels for you to choose from. If you are using something else or want to build from source, you can use this notebook to build the library.
I have written a notebook to build xformers from source. You can use it to build xformers for your own GPU.
- stable_diffusion_1_5_webui.ipynb
- Bypass colab detection #20
- stable_diffusion_1_5_webui.ipynb
- Upgrade webui version
- Upgrade some extensions' version
- Change some extensions git url to original repo
- stable_diffusion_1_5_webui.ipynb
- Change
KoreanDollLikeness
download url to @kanbara's huggingface model - Add
KoreanDollLikeness v2
model - Fix PyTorch and torchvision version conflict problem #17
- Change
- stable_diffusion_1_5_webui.ipynb
- Download Lora into official model directory instead of the plugin directory
- Soft link the lora models to the Additional Network plugin directory
- stable_diffusion_1_5_webui.ipynb
- Support input custom lora download url
- stable_diffusion_1_5_webui.ipynb
- Use the wrong list to cause the Textual Inversion download to fail
- Only soft link the model once, remove the
!rm -rf stable_diffusion/model/Lora
step to avoid accidentally deleting other models
- lora_train.ipynb
- Language Internationalization
- stable_diffusion_1_5_webui.ipynb
- Support Cloudfared as a Tunnel Client
- README
- Modify Chilled_re_generic_v2 link to Google Drive Share Link
- Set
Chilloutmixss
model to deprecated (This model is disappeared.)
- stable_diffusion_1_5_webui.ipynb
- Remove
Chilloutmixss
model option - Use
try-except
to catchKeyError
when downloading models. - Support download
styles.csv
with url.
- Remove
- README
- Add Chilled_re_generic_v2 download link
- stable_diffusion_1_5_webui.ipynb
- Support custom checkpoint name ( From custom url )
- stable_diffusion_1_5_webui.ipynb
- Custom checkpoint version
- Missing return value
- API argument support
- Fixed xformer not starting on M4000 GPU platforms with xformer installed
- Support download multiple checkpoints at the same time
- Support download checkpoints from other URLs
- stable_diffusion_1_5_webui.ipynb
- Download
koreanDollLikeness
model with GitHub Release API - Soft link LoRA models so that they can be used in prompts and additional networks. (Only operate before startup, the LoRA installed after startup may not be used in prompts. You need to restart the application to re-link the models installed in other networks.)
- Provides the option to install LoRA before startup
- Get the latest checkpoint download address from the CivitAI API
- Support for entering custom checkpoint id
- Define download functions to optimize readability
- Support LoRA specific version selection in download function
- Auto detect download tool
- Textual Inversion download function
- Download
- README.md
- Update "Experimental Checkpoints" and "Experimental LoRA" section
- prompts.md
- Add a new prompt
Basic Tiara
- Add a new prompt
- README.md
- Update Experimental Lora List - Add
ChilloutMixss
- Optimize CHANGELOG format
- Internationalize README
- New "Textual Inversion" section
- Add "NoteBook Built-in Extension" section
- Add "Build xformers from source" section
- Update Experimental Lora List - Add
- lora_train.ipynb
- Fix serious errors in LoRA training script
- Remove unnecessary platform and GPU checks
- Add
export_model_dir
option to specify the directory where the model is exported - Add an extra build installation xformers option for the M4000 GPU
- Use
ninja
to build xformers much faster ( Followed by Official README)
- stable_diffusion_1_5_webui.ipynb
- Add an extra build installation xFormer option for the M4000 GPU
- Use
ninja
to build xformers much faster ( Followed by Official README)
- prompts.md
- Internationalize
- xformers_build.ipynb
- New xformers build script
- Switch xformers source version to 0.0.16
- workflows
- Add
xformers_build.ipynb
to Preview CI - Remove
pull_request_target
value to prevent the workflow from running twice
- Add
- Release
- Publish xformers precompiled wheels for M4000 GPU
- workflows
- Automatically comment on Preview link when Pull Request ( #2 )
- stable_diffusion_1_5_webui.ipynb
- Install controlnet, openpose-editor, Kohya sd-scripts extension with Stable-Diffusion-WebUI
- Remove the old training model installation scheme and merge it into the installation steps ( created in 2023.2.19 )
- lora_train.ipynb
- New Lora Train Script ( Alpha )
- stable_diffusion_1_5_webui.ipynb
- Better option selection mechanism
- Fine distinction between Paperspace and Colab platforms rather than relying on a single Free GPU model
- stable_diffusion_1_5_webui.ipynb
- Fix the problem of incorrectly identifying the Quadro M4000 GPU
- Add Training Model Installation Scheme ( Power by d8ahazard/sd_dreambooth_extension)
- Optimize checkpoint selection
- Fix the problem of not being able to read variables
- Automatically check whether webUI and training extensions are installed
- stable_diffusion_1_5_webui.ipynb
- Update the latest version of the upstream ChilloutMix
- Update Prompts Collection
- Compatible with Paperspace platform (Free GPU)
- Export all generated images
- Use
nvidia-smi
to view GPU information - Check if GPU supports Xformers
- Optimize variable passing
- stable_diffusion_1_5_webui.ipynb
- Add SunshineMix Checkpoint as a second choice for 2.5D painting
- stable_diffusion_1_5_webui.ipynb
- Because there may be a sudden exit in the middle, there is another way to restart
Created by @wibus-wee
Reference: camenduru/stable-diffusion-webui-colab