底模：Pony
主页：https://civitai.com/models/423315/all-characters-honkai-impact-3rd-3
版本：v1.0
|
Trigger Words |
ALL IN ONE |
崩坏3全角色使用指南 Guide for All Characters in Honkai Impact 3
提示词文档：
崩坏3全角色使用指南 Guide for All Characters in Honkai Impact 3
More Character:
Collection of All Character in One Models 全角色模型合集
v1.0版本使用2w左右张图片训练。(最新的一张图片来自2024.6.6)
相比v0.9版本，支持更多角色，
训练集中包含大量多人图片。
包含同一个角色的不同皮肤.
为了防止角色特征互相污染，使用全部特征标签训练。
覆盖了图片素材比较多的主要角色，但仍有部分角色和服装不能直出。
The v1.0 version was trained using approximately 20,000 images. (The latest image is from June 6, 2024).
Compared to the v0.9 version, it supports a greater variety of characters.
The training dataset includes a significant number of group images.
It includes different skins of the same character.
To prevent feature contamination among characters, the model was trained with all feature labels.
It covers most of the major characters with a substantial amount of image material. However, there are still some characters and outfits that cannot be accurately generated.
Taining model: Pony
Recommend PONY model: Movable figure model Pony/T-ponynai3/AutismMix SDXL
Training resolution: 1024*1024
Recommended output resolution: 832*1216
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/waifuset
注意，当前版本依然是未完成品，因为没有对少图角色的做平衡，仅覆盖了部分主要角色
Please note that the current version is still a work in progress as it lacks balance in representing characters with fewer images. It only covers a subset of the main characters.
数据截至到2024年4月19日。
持续更新中。
v0.9版本使用16138张图片训练。(最新的一张图片来自2024.4.19)
训练集中包含大量多人图片。
包含同一个角色的不同皮肤.
为了防止角色特征互相污染，使用全部特征标签训练。
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。
Version 0.9 was trained using 16138 images.(The latest image is from 2024.4.19)
The training set includes a large number of images with multiple people.
It includes different skins of the same character.
To prevent feature contamination among characters, all feature tags were used for training.
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.
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 : Nya 的显卡租借
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-
--
Playable
kiana_kaslana_(white_comet),silver hair,very long hair,twin braids,ahoge,bangs,blue eyes,medium breasts,bodysuit,hairband,cleavage cutout,hair ornament,
Introduced in Part 2
ELF (Equipment: Living Form)
Collaborator (Part 2)
A Post-Honkai Odyssey Characters