2.0版本更新

该版本共使用10360张图训练，以下是支持的所有角色以及训练集对应的数量：

Version 2.0 Update

This version was trained on a total of 10,360 images. Below is a list of all supported characters along with the corresponding number of examples in the training set.

 gotoh_hitori: 5032
 kita_ikuyo: 2432
 ijichi_nijika: 2338
 yamada_ryo: 2066
 hiroi_kikuri: 1276
 pa-san: 495
 ijichi_seika: 447
 gotoh_futari: 129
 gotoh_michiyo: 70

The model supports a total of 4 characters and was trained using 4,211 images. Each character has a minimum of 500 images, and special inclusion was made for dual and multiple character illustrations.

prompt:

(score_9,score_8_up,score_7_up,score_6_up,score_5_up,score_4_up

Negative prompt:

(score_4,score_5,score_3,score_2,score_1)

感谢我的朋友@Tonade 提供的四人封面。

Training model: Pony Diffusion V6 XL

Inference model: Pony Diffusion V6 XL / T-ponynai3

Training resolution: 1024*1024

Recommended output resolution: 1024*1280

Recommended model weight: 0.8~1

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-manager