ponyv6_noobV1_2_adamW-000017

Prompt

分区书写的提示词。原图包含工作流信息，可以在ComfyUI中查看。Areal writen prompt. Original image contains workflow information, you can check it in ComfyUI.

Negative Prompt

hair ornament, bowtie, halo, worst quality, low quality, displeasing, hair intakes, old, text

Prompt

masterpiece, best quality, very aesthetic, 1girl, solo, red hair, purple eyes, long hair, blunt bangs, parted lips, lipsick, half-closed eyes, looking at viewer, white gown, strapless, cleavage, frilled dress, holding champagne, champagne flute, upper body, from below, light, sidelighting, colorful background, dark background, dim

Negative Prompt

worst quality, low quality, displeasing, hair intakes, old

Prompt

(ComfyUI Workflow)

Negative Prompt

tiara, hair ornament, bowtie, worst quality, low quality, displeasing, hair intakes, old, text

Model description

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。

Source

https://civitai.com/models/856285?modelVersionId=1247042

Credit

https://civitai.com/user/Dajiejiekong

Trigger words

You should use None to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.