(pony) Touhou characters ( 115 characters) 东方全角色115位

115位角色，以每个角色200张单人图为目标，最后一共收集到22974 张图片。

v1版本的115位角色是单人图数量大于200张的角色。

后续版本会加角色，我本地电脑还有58个角色文件夹没有加进去。

从收集素材到发布，大概耗费了2周时间。

在单卡4090上共训练了50+小时。

我花8个小时写了一份提示词文档，以方便用户查找使用。

我后面会训练其他系列的全角色，比如崩坏星穹铁道、崩坏3、碧蓝航线、明日方舟、fgo，以及新出的绝区零等等。

因为是业余时间在做这个系列，我无法为每一位角色都创建单独的示例图像，因此模型的反馈和优化建议，就拜托大家了。

提示词文档：Guide to All Characters in the Touhou Project 东方全角色使用指南 (Continuously Updating) 2024.4 | Civitai

There are a total of 115 characters, with a target of 200 solo images per character. In the end, a collection of 22,974 images was gathered.

The v1 version includes the 115 characters with more than 200 solo images each.

Future versions will add more characters. I have 58 character folders on my local computer that haven't been included yet.

From collecting the materials to the release, it took approximately two weeks.

A total of 50+ hours of training was conducted on a single 4090 graphics card.

I spent 8 hours writing a document with prompt words to facilitate user searches and usage.

In the future, I will train full character sets for other series such as Honkai Star Rail, Honkai Impact 3rd, Azur Lane, Arknights, Fate/Grand Order (FGO), as well as the newly released Absolute Area Zero, and more.

Since I am working on this project in my spare time, I cannot create individual example images for each character. Therefore, I rely on feedback and optimization suggestions from users for the model's improvement.

How to use：Guide to All Characters in the Touhou Project 东方全角色使用指南 (Continuously Updating) 2024.4 | Civitai

Please note that this model's content includes some covers that have been rated as PG-13/R/X

Please choose the appropriate age rating based on your needs.

Training model: Pony

Recommend model: Pony Diffusion V6 XL/T-ponynai3/AutismMix SDXL

Training resolution: 1024*1024

Recommended output resolution: 1024*1280

特别鸣谢：算力赞助 nieta.art / GPU Sponsor: Neta

Discord : https://discord.com/invite/CFpyHceF52

Recommended dataset collection and processing tools: https://github.com/deepghs/waifuc

Possibly the most user-friendly dataset processing UI currently in use： https://github.com/Eugeoter/sd-dataset-