模型推荐:Counterfeit 实验性，高细节，动漫风

#模型推荐:Counterfeit 实验性，高细节，动漫风| 来源: 网络整理| 查看: 265

最新版本Counterfeit模型:https://huggingface.co/gsdf/Counterfeit-V2.5

“V2.5 已更新为易于使用的动漫风格模型。

我将此嵌入用于否定提示(Negative Embedding)。https://huggingface.co/datasets/gsdf/EasyNegative

副产品分享

V2.1…使用感觉类似V2.0V2.2…NSFW模型”

((masterpiece,best quality)),1girl, solo, animal ears, rabbit, barefoot, knees up, dress, sitting, rabbit ears, short sleeves, looking at viewer, grass, short hair, smile, white hair, puffy sleeves, outdoors, puffy short sleeves, bangs, on ground, full body, animal, white dress, sunlight, brown eyes, dappled sunlight, day, depth of field Negative prompt: EasyNegative, extra fingers,fewer fingers, Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 10, Size: 448x768, Denoising strength: 0.6, Hires upscale: 1.8, Hires upscaler: Latent((masterpiece,best quality)),2girls, black kimono, black legwear, black ribbon, black hair, cherry blossoms, day, flower, hair bun, hair ribbon, japanese clothes, kimono, long hair, looking at viewer, looking back, multiple girls, obi, outdoors, red eyes, red hair, ribbon, sandals, single hair bun, stairs, standing, statue, torii, tree, white kimono, yellow eyes Negative prompt: EasyNegative, extra fingers,fewer fingers, Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 10, Size: 640x960, Denoising strength: 0.58, Hires upscale: 1.8, Hires upscaler: Latent((masterpiece,best quality))1girl, solo, black skirt, blue eyes, electric guitar, guitar, headphones, holding, holding plectrum, instrument, long hair, , music, one side up, pink hair, playing guiter, pleated skirt, black shirt, indoors Negative prompt: EasyNegative, extra fingers,fewer fingers, ((masterpiece,best quality)),1girl, bangs, blue eyes, blurry background, branch, brown hair, dappled sunlight, flower, from side, hair flower, hair ornament, japanese clothes, kimono, leaf, (maple leaf:1.9), obi, outdoors, sash, solo, sunlight, upper body Negative prompt: EasyNegative, extra fingers,fewer fingers, Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 10, Size: 864x512, Denoising strength: 0.58, Hires upscale: 1.8, Hires upscaler: Latent

训练的Negative Embedding：https://huggingface.co/datasets/gsdf/EasyNegative

"这是使用 Counterfeit 训练的否定提示(Negative Embedding)。请在“\stable-diffusion-webui\embeddings”文件夹中使用。它可以与其他模型一起使用，但效果不确定。"

Counterfeit-V2.0.safetensorsAbyssOrangeMix2_sfw.safetensors

使用模型生成的较差结果图像来训练Embedding，放入Negative来提升质量。类似利用坏的手部图像训练Embedding,加入Negative后来降低出现手部崩坏的机率，是一种不错思路，但提升空间有多大见仁见智。

原文及下载：

https://huggingface.co/gsdf/Counterfeit-V2.5/tree/main

https://huggingface.co/datasets/gsdf/EasyNegative/tree/main

【本文地址】

公司简介

联系我们