Stable Diffusion 个人推荐的各种模型及设置参数、扩展应用等合集（不断更新中）

一、说明

• | 表示或者
• + 表示 以上

二、模型

适用风景、房子、车子等漫画类风格

模型的VAE不要用模型附带的，好像就是naifu的官方vae，很老了，用 vae-ft-mse-840000-ema-pruned.ckpt 或者是 kl-f8-anime2.ckpt；
嵌入模型要下载作者推荐的负面关键词汇总的 EasyNegative，下载后放到 embeddings 文件夹内，tag EasyNegative 才会起效。

参数：

• Checkpoint: Counterfeit-V2.5.safetensors [bd83b90a2e]
• VAE: vae-ft-mse-840000-ema-pruned.ckpt
• Clip skip: 2
• Sampling steps: 20+
• Sampling method: DPM++ 2M Karras | DPM++ SDE Karras
• Prompt: (masterpiece, best quality, very detailed, Ultra HD: 1.2) | (((masterpiece))), (((best quality))), (((extremely detailed))), Depth of field, illustration, shiny, pastel color,

案例：

(masterpiece, best quality, very detailed, Ultra HD: 1.2)
Negative prompt:  EasyNegative, nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, bad feet,
Seed: 31337, Steps: 32, Sampler: DPM++ SDE Karras, CFG scale: 7

下载：
Checkpoint：https://huggingface.co/gsdf/Counterfeit-V2.5
VAE：https://huggingface.co/Yukihime256/840000/tree/main
EasyNegative：https://civitai.com/models/7808/easynegative

来源：
强烈推荐的超细节风格化模型和参数

古风

水彩国画风

参数：

• Checkpoint: dalcefo_painting
• Clip skip: 2
• Sampling steps: 20+
• Sampling method: DPM++ 2M Karras | DPM++ SDE Karras
• Prompt: <(masterpiece, realistic:1.3), (extremely intricate:1.2)>,

案例：

<(masterpiece, realistic:1.3), (extremely intricate:1.2)>, portrait of a girl, face, close up, pointy ears, dress, half-closed eyes, jewelry, sitting, strapless, strapless dress, breasts, watermark, bare shoulders, tiara, grey dress, cleavage, long hair, braid, grey hair, long eyelashes, solo, profile, solo, elf,
Negative prompt: (worst quality, low quality:1.4), (depth of field, blurry:1.2), (greyscale, monochrome:1.1), 3D face, cropped, lowres, text, jpeg artifacts, signature, watermark, username, blurry, artist name, trademark, watermark, title, multiple view, Reference sheet, curvy, plump, fat, muscular female, strabismus,
Size: 520x680, Seed: 285145899, Model: dalcefo_v3_painting3, Steps: 26, Sampler: DPM++ 2M Karras, CFG mode: Linear Up, CFG scale: 15, Clip skip: 2, Mimic mode: Linear Up, Model hash: 7107c05c1c, Mimic scale: 15, Hires upscale: 1.5, Hires upscaler: Latent (nearest-exact), CFG scale minimum: 0, Denoising strength: 0.5, Mimic scale minimum: 0, Threshold percentile: 100, Dynamic thresholding enabled: True

可写实的综合体

这个模型融合了多个模型（比如2.2版本融合了f222_v1.ckpt、elldrethSLucidMix_V10.cpkt、hassanBlendAllVersio_hassanBlend14.ckpt、seek_art_mega_v1.ckpt (license)、modelshoot-1.0.ckpt），并且2.2版是在stable diffusion1.5的基础上训练出来的，可以使用明星脸，而2.0以后的版本对明星脸进行了限制。
可以用关键字设置相机角度和人物动作

参数：

• Checkpoint: Protogen x5.8 Rebuilt (Scifi+Anime) Official Release | Protogen x5.3 (Photorealism) Official Release | Protogen x3.4 (Photorealism) Official Release | Protogen v2.2 (Anime) Official Release
• Clip skip: 2
• Sampling steps: 20+
• Sampling method: DPM++ 2M Karras | DPM++ SDE Karras
• Prompt: (from_above:1.3) | (from_below:1.3) | (from_side:1.3) | (from_behind:1.3) | (hand_on_hip:1.2) | (sitting:1.2)
• Trigger Words: MODELSHOOT STYLE | NOUSR ROBOT

案例：

(sitting:1.2),modelshoot style, (extremely detailed 8k wallpaper),a medium shot photo of a sexy female soldier,  American ERDL Lowland CAMO, Intricate, High Detail, dramatic,  elite military forces real world, fantastic location, battle environment, rugged harsh situation soldier, action shot, skin pores, very dark lighting, heavy shadows, detailed, detailed face, (vibrant, photo realistic, realistic, dramatic, dark, sharp focus, 8k), (weathered greasy dirty damaged old worn military soldier outfit:1.3),
Negative prompt: Asian, black and white, close up, cartoon, 3d, denim, (disfigured), (deformed), (poorly drawn), (extra limbs), blurry, boring, sketch, lackluster, signature, letters, watermark, low res , horrific , mutated , artifacts , bad art , gross , b&w , poor quality , low quality , cropped
Seed: 452943117, Steps: 30, Sampler: DPM++ SDE Karras, CFG scale: 7

RPG 游戏人物类

可根据职业（巫师、战士等）、衣物（皮甲、布甲等）进行规划

参数：

• Checkpoint: rpg_V4
• Clip skip: 2
• Sampling steps: 30+
• Sampling method: DPM++ 2M Karras | DPM++ SDE Karras

案例：

full body shot photo of the most beautiful artwork in the world featuring a modern female (rogue thief:1.1) wearing multiple layer (leather armor:1.1), sexy, big eyes, urban tokyo futuristic look, neon lights, night, slow motion, reflections, orange raincoat, intricate detail, nostalgia, high boots, heart professional majestic oil painting by Ed Binkley, Atey Ghailan, Studio Ghibli, by Jeremy Mann, Gregory Manchess, Antonio Moro, trending on ArtStation, trending on CGSociety, Intricate, High Detail, Sharp focus, dramatic, photorealistic painting art by midjourney and greg rutkowski,
Negative prompt: cartoon, 3d, ((disfigured)), ((bad art)), ((deformed)),((extra limbs)),((extra barrel)),((close up)),((b&w)), weird colors, blurry,(((duplicate))), ((morbid)), ((mutilated)), [out of frame], extra fingers, mutated hands, ((poorly drawn hands)), ((poorly drawn face)), (((mutation))), (((deformed))), ((ugly)), blurry, ((bad anatomy)), (((bad proportions))), ((extra limbs)), cloned face,(((disfigured))), out of frame, ugly, extra limbs, (bad anatomy),gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), mutated hands, (fused fingers), (too many fingers), (((long neck))), (((tripod))), (((tube))), Photoshop, video game, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy, 3d render, (((umbrella))

关于AI绘画技术储备

学好 AI绘画 不论是就业还是做副业赚钱都不错，但要学会 AI绘画 还是要有一个学习规划。最后大家分享一份全套的 AI绘画 学习资料，给那些想学习 AI绘画 的小伙伴们一点帮助！

对于0基础小白入门：

如果你是零基础小白，想快速入门AI绘画是可以考虑的。

一方面是学习时间相对较短，学习内容更全面更集中。
二方面是可以找到适合自己的学习方案

包括：stable diffusion安装包、stable diffusion0基础入门全套PDF，视频学习教程。带你从零基础系统性的学好AI绘画！

需要的可以微信扫描下方CSDN官方认证二维码免费领取【保证100%免费】

1.stable diffusion安装包 （全套教程文末领取哈）

随着技术的迭代，目前 Stable Diffusion 已经能够生成非常艺术化的图片了，完全有赶超人类的架势，已经有不少工作被这类服务替代，比如制作一个 logo 图片，画一张虚拟老婆照片，画质堪比相机。

最新 Stable Diffusion 除了有win多个版本，就算说底端的显卡也能玩了哦！此外还带来了Mac版本，仅支持macOS 12.3或更高版本。

2.stable diffusion视频合集

我们在学习的时候，往往书籍代码难以理解，阅读困难，这时候视频教程教程是就很适合了，生动形象加上案例实战，一步步带你入门stable diffusion，科学有趣才能更方便的学习下去。

3.stable diffusion模型下载

stable diffusion往往一开始使用时图片等无法达到理想的生成效果，这时则需要通过使用大量训练数据，调整模型的超参数（如学习率、训练轮数、模型大小等），可以使得模型更好地适应数据集，并生成更加真实、准确、高质量的图像。

4.stable diffusion提示词

提示词是构建由文本到图像模型解释和理解的单词的过程。可以把它理解为你告诉 AI 模型要画什么而需要说的语言，整个SD学习过程中都离不开这本提示词手册。

5.AIGC视频教程合集

观看全面零基础学习视频，看视频学习是最快捷也是最有效果的方式，跟着视频中老师的思路，从基础到深入，还是很容易入门的。

实战案例

纸上得来终觉浅，要学会跟着视频一起敲，要动手实操，才能将自己的所学运用到实际当中去，这时候可以搞点实战案例来学习。

这份完整版的学习资料已经上传CSDN，朋友们如果需要可以微信扫描下方CSDN官方认证二维码免费领取【保证100%免费】