检查链接：试试我的新模型！

V 2.5 SPO

• 在此版本中，我改进了风格、解剖结构、一致性和创造力。
  - 该模型开始无法良好还原艺术家的风格。

提示词：

artist:, {prompt}
very awa, masterpiece, best quality, high quality, newest, recent, year 2024, absurdres, 

负面提示词 S：

very as2, worst aesthetic, good quality, normal quality, low quality, bad quality, worst quality, mid, early, old, lowres, low res, thumbnail, scan artifacts, jpeg artifacts,

负面提示词 XL：（可根据需要自行使用 S 版本）

very as2, worst aesthetic, good quality, normal quality, low quality, bad quality, worst quality, mid, early, old, lowres, low res, thumbnail, scan artifacts, jpeg artifacts, compression artifacts, lossy-lossless, adversarial noise, ai-generated, ai-assisted, abstract, official art, 4koma, multiple views, reference sheet, dakimakura \(medium\), turnaround, comic, greyscale, monochrome, sketch, unfinished, watermark, logo, signature, text, artist name, dated, username, web address, bad hands, bad feet, extra digits, fewer digits, extra arms, extra faces, multiple heads, missing limb, amputee, severed limb, mutated hands, distorted anatomy, blurry, off-topic, artistic error, bad proportions, bad perspective, bad anatomy, what, meme, tagme, censored, copyright name, copyright symbol, resized, downscaled, source larger, ugly, aliasing, simple background, asymmetrical, concept art, cropped, bleed through, crease, bad aspect ratio, derivative work, MD5 mismatch, moire, third-party edit, image sample, upscaled, Waifu2x, unmoving pattern, third-party watermark, has bad revision, doesnotexist, 

V 1.0

请留下您的评论和几组生成结果，这将极大帮助模型的改进。

此模型相较于原始版本在所有参数上均有提升。

主要改进在于无伪影的解剖结构与细节表现。

缺点是提示词敏感度有所降低。

采样方法：Euler a
步数：28
CFG：5-7
VAE：SDXL VAE

提示词：

artist:, {prompt}
masterpiece, best quality, good quality, newest, very awa, absurdres, highres, 

负面提示词 S：

worst quality, worst aesthetic, bad quality, normal quality, average quality, oldest, old, early, 

负面提示词 XL：（可根据需要自行使用 S 版本）

adversarial noise, ai-generated, ai-assisted, stable diffusion, nai diffusion, worst quality, worst aesthetic, bad quality, normal quality, average quality, oldest, old, early, very displeasing, displeasing, unknown artist, banned artist, what, off-topic, artist request, text, artist name, signature, username, logo, watermark, copyright name, copyright symbol, resized, downscaled, source larger, low quality, lowres, jpeg artifacts, compression artifacts, blurry, artistic error, bad anatomy, bad hands, bad feet, disfigured, deformed, extra digits, fewer digits, missing fingers, censored, bar censor, mosaic censoring, missing, extra, fewer, bad, hyper, error, ugly, worst, tagme, unfinished, bad proportions, bad perspective, aliasing, simple background, asymmetrical, monochrome, sketch, concept art, flat color, flat colors, simple shading, jaggy lines, traditional media \(artwork\), microsoft paint \(artwork\), ms paint \(medium\), unclear, photo, icon, multiple views, sequence, comic, 2koma, 4koma, multiple images, turnaround, collage, panel skew, letterboxed, framed, border, speech bubble, 3d, lossy-lossless, scan artifacts, out of frame, cropped, abstract, doesnotexist, 

配方：

0.5(sd_noobaiXLNAIXL_epsilonPred11Version) + 0.5(sd_Illustrious-XL-v0.1) + 0.5(0.5(sd_cyberrealisticXL_v31) + 0.5(sd_stoiqoNewrealityFLUXSD35_XLPRO) - sd_sdXL_v10VAEFix)

非常感谢这些模型的作者！

• NoobAI-XL

• CyberRealistic XL

• STOIQO NewReality

• Illustrious-XL