Intro. 简介：

A style LoCon trained on pony-based model images collected from Civitai site with "most collections" and "most reactions".

这是一个训练自Civitai上点赞最多和收藏最多的pony系模型图片的画风LoCon。

This lora does not intend to simulate any specific artist style or technique. It MIGHT reflects community taste and the visual attractiveness of a picture to a certain extent. Styles may change subtly depending on different prompts.

这个lora并不意于还原某个特定的画师画风或者绘画技巧。它在某种程度上可能反应了社区审美和图片的视觉吸引力。 不同的提示词下可能会有微妙的画风变化。

Usage 使用方法：

Versions before V2 do not have specific trigger words. Please use the quality tags provided with the corresponding model.

For V3 and later versions, the following tags were trained:

V2以前的版本没有特定触发词。请使用对应模型自带的质量提示词。

对于v3及后续版本，训练了以下标签：

positive:

masterpiece, best quality, very aesthetic

negative:

worst quality, low quality, displeasing

你可以在此基础上编辑提示词。

Data Generation 数据版本：

v6:

Added over 500 new images, some of which are selected from Flux. I removed some older images that I deemed to be of lower quality.

The total number of images in data set now exceeds 3,000, with more than 20 concepts manually enhanced/edited across 6 versions of the dataset.

The model’s rank has been increased as well.

新添加了500+张图片其中有一部分选自flux生成的图像。删除了一部分我认为品质不佳的旧图片。

现在总的图片数超过了3000，6个版本的数据总共手动增强/修正了20多条概念。

增加了模型的rank。

v5.9:

The model's performance is not as expected, but I believe the images in the training data set are just fine. I'm planning to adjust the tags manually and see how will the results change.

模型效果不如预期，但是我觉得训练集的图片本身应该没什么问题。打算先手动修正tag看看效果。

2025/1/3更新：

Manually updated some tags, but they seem unrelated to brightness and colors. Tentatively guessing it might be related to noise offset.

手动更新了一部分标签，但是它们和明暗色彩无甚干系。暂时猜测可能和noise offset有关。