v8

肌理更新：强化了以下tag的学习：

Texture Update: The following tags have been reinforced in training:

realistic, photorealistic, flat color,

shiny skin, matte skin, shiny hair,

请注意，在danbooru数据集中有很多个用于描述“照片”和“接近照片的风格”的tag。我在训练集中统一标注这些图片为“photorealistic”。但是使用danbooru训练集训练的SDXL模型大多并不能很好地画出写实图像，因此“photorealistic”只建议在较小权重下用于改变画面的肌理。“realistic”可以在高权重下正常运作。

Please note that Danbooru dataset contains multiple tags to describe "photo" or "photo-like styles". I’ve tagged all such images as “photorealistic” in dataset.

However, most SDXL models trained on the Danbooru dataset do not render realistic images well. “photorealistic” is only recommended at low weight, where it can help adjust texture rather than create realism images. The “realistic” tag can work properly at higher weight.

快速上手 | Quick Start

这是什么？ | What is this?

• Pony: People's Works （ppw）是一个实验性的微调模型系列，数据集有约85%是收集自CivitAI上用户发表的AI生成图片。早期ppw的数据集最初建立在由pony v6生成图片的基础上，因此本系列模型生成的图片也带有pony diffusion的特征。

• 本系列模型使用标准Danbooru标签，主要擅长生成中、近景风格化人像。它们的主要功能是使基础模型可以在不使用画师串、较少的质量提示词的条件下获得相对稳定的图像质量，为提示词节约token空间。
  本模型并非风格模型，在不同的提示词和生成条件下可能会有微妙的画风差异。

• Pony: People's Works (ppw) is a experimental fine-tuned model series, approximately 85% of the dataset comes from AI-generated images published by users on CivitAI. Since the earlier ppw dataset was built on images generated by Pony V6, the outputs of this series also carry some characteristics of Pony Diffusion.

• This series uses standard Danbooru tags and is mainly optimized for generating stylized portraits at medium and close range. The primary effect of this model series is to allow the basemodel to achieve relatively stable image quality, without artist keywords or long quality tags, freeing up token space for prompts.
  These models are not style LoRAs. There may be subtle stylistic variations depending on different prompts and generating conditions.

版本信息 | Version Info.

• 本页面发布的是ppw的高维LoCon版本，也是这个项目的主页面。

• LoCon版本的ppw可以灵活搭配各类功能LoRA和底模，并且效果强度有更高的可控性。高维度版本的LoCon拥有更强的泛化性和细节表现，但是会占用更多的储存空间和计算资源。

• 主要用于在线生成服务和供机器性能较强的用户本地生成使用。

• This page features the high dim LoCon version models of ppw, which also serves as the main page of this project.

• The LoCon versions of ppw can be flexibly combined with various functional LoRAs and checkpoints, offering greater controllability over effect weight. High dimension versions provide stronger generalization and more detailed rendering, but it requires more storage space and computational resources.

• They are mainly intended for online generation services and local use by users with high-performance PCs.

精简版LoCon | Lightweight LoCon ver.

基础模型版 | Checkpoint versions (Illustrious)

基础模型版 | Checkpoint versions (NoobAI)

更多 | more

使用方法 | Usage

positive:

masterpiece, best quality, very aesthetic

negative:

low quality, displeasing