AI Rank
EN
← 开源
hollowstrawberry

kohya-colab

Accessible Google Colab notebooks for Stable Diffusion Lora training, based on the work of kohya-ss and Linaqruf

Model DevelopmentDataset engineeringFine-tuningJupyter Notebook
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
822
Star
137
Fork
+1
本周
6
贡献者
创建于 2023-03-23 · 更新于 2026-10-13 · 今日第 13465 名
主要开发者
hollowstrawberryMonkeyDLuffy18darkmyu

hollowstrawberry/kohya-colab 排名第 13,465，有 822 个星标。

同类别比较

hollowstrawberry/kohya-colab 排名第 13,465，此处有 8 个同类条目；facebookresearch/vilbert-multi-task 排名第 13,464。

同类别比较
名称排名指标
lucidrains/PaLM-pytorch13,456
语言:
Python
星标数:
823
分叉数:
80
简介:
Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways
sail-sg/Adan13,458
语言:
Python
星标数:
823
分叉数:
73
简介:
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
bubbliiiing/yolov4-tiny-pytorch13,462
语言:
Python
星标数:
822
分叉数:
183
简介:
这是一个YoloV4-tiny-pytorch的源码，可以用于训练自己的模型。
facebookresearch/vilbert-multi-task13,464
语言:
Jupyter Notebook
星标数:
822
分叉数:
174
简介:
Multi Task Vision and Language
tkipf/relational-gcn13,469
语言:
Python
星标数:
822
分叉数:
130
简介:
Keras-based implementation of Relational Graph Convolutional Networks
andyzeng/tsdf-fusion13,473
语言:
Cuda
星标数:
821
分叉数:
135
简介:
Fuse multiple depth frames into a TSDF voxel volume.
nashory/pggan-pytorch13,477
语言:
Python
星标数:
821
分叉数:
132
简介:
:fire::fire: PyTorch implementation of "Progressive growing of GANs (PGGAN)" :fire::fire:
rdiankov/openrave13,478
语言:
C++
星标数:
821
分叉数:
358
简介:
Open Robotics Automation Virtual Environment: An environment for testing, developing, and deploying robotics motion planning algorithms.
关键参数与规格
关键参数与规格
参数值
语言Jupyter Notebook
类别Model Development
子类别Dataset engineering,Fine-tuning
关键词Datasets, Image production, No code/Low code, Text-to-image
星标数822
分叉数137
贡献者6
创建日期2023-03-23
更新日期2026-10-13
1 天星标数0
7 天星标数1
排名13,465
上次排名13,358
排名变化-107
7 天星标排名10,610
上次 7 天星标排名10,662
7 天星标排名变化52
总星标排名13,038
上次总星标排名13,016
总星标排名变化-22
国家Chile
README 摘录

Kohya Colabs Accessible Google Colab notebooks for Stable Diffusion Lora training, based on the work of kohya-ss and Linaqruf. Finds duplicate images using the FiftyOne open-source software. Displays the user's dataset back to them through the FiftyOne interface so that they may manually curate their images. Able to generate tags for all your anime images using the Waifu Diffusion 1. Able to generate captions for all your images using the BLIP model. Gives you the ability to edit

hundreds of text files at once, to add/remove/replace tags inside them dynamically. Works inside your Google Drive by default. 🌟 XL Lora Trainer Can train LoRA and LoCon for Stable Diffusion XL, includes several model options for anime. One click to install and start training. Can work with multiple colab configurations, including T4 (free) and A100. Offers most parameters while setting useful values behind the scenes to keep it simple. Allows you to optionally define multiple folders for training

. Uses the latest technologies to train quickly. Works inside your Google Drive by default and connects easily with Dataset Maker.

常见问题

记录了多少星标和分叉？

hollowstrawberry/kohya-colab 有 822 个星标和 137 个分叉。

仓库排名是多少？

hollowstrawberry/kohya-colab 排名第 13,465。

记录的语言和类别是什么？

hollowstrawberry/kohya-colab 有 822 个星标，语言为 Jupyter Notebook，类别为 Model Development。

哪个仓库排名最接近？

hollowstrawberry/kohya-colab 与 facebookresearch/vilbert-multi-task 比较，后者排名第 13,464，有 822 个星标。

README

Kohya Colabs

Accessible Google Colab notebooks for Stable Diffusion Lora training, based on the work of kohya-ss and Linaqruf.

If you need support I now have a public Discord server

You can support me on Buy me a coffee

🇬🇧 English 🇪🇸 Spanish
📊 Dataset Maker
⭐ Lora Trainer
🌟 XL Lora Trainer -
🌟 Legacy XL Trainer -
Lora making Guide Click Here -
Stable Diffusion guide Click Here Click Aquí

📊 Dataset Maker - Features

  • Able to scrape hundreds of images from the popular anime gallery Gelbooru, that match the conditions set by the user.
  • Finds duplicate images using the FiftyOne open-source software.
  • Displays the user's dataset back to them through the FiftyOne interface so that they may manually curate their images.
  • Able to generate tags for all your anime images using the Waifu Diffusion 1.4 Tagger model.
  • Able to generate captions for all your images using the BLIP model.
  • Gives you the ability to edit hundreds of text files at once, to add/remove/replace tags inside them dynamically.
  • Works inside your Google Drive by default.
  • Connects easily with Lora Trainer.

🌟 XL Lora Trainer

  • Can train LoRA and LoCon for Stable Diffusion XL, includes several model options for anime.
  • One click to install and start training.
  • Can work with multiple colab configurations, including T4 (free) and A100.
  • Offers most parameters while setting useful values behind the scenes to keep it simple.
  • Allows you to optionally define multiple folders for training.
  • Uses the latest technologies to train quickly.
  • Works inside your Google Drive by default and connects easily with Dataset Maker.

 

排名相邻
同类项目