🚀 DeDeDe模型

DeDeDe是一款经过调整的Stable Diffusion模型，旨在更轻松地输出动漫风格的人物形象。它结合了多个优质模型的特点，并经过大量数据的微调，能为用户带来出色的动漫图像生成体验。

🚀 快速开始

如果您能阅读英文，请参考这里。在使用本模型前，请务必充分确认以下的许可内容。

✨ 主要特性

• 动漫风格输出：擅长生成动漫风格的人物图像，满足动漫爱好者的需求。
• 多模型融合：基于DreamLike Diffusion 1.0，融合了Trinart Characters v2 Derrida，并经过DreamLike Photoreal 1.0的调整和大量图像的微调。

💻 使用示例

基础用法

推荐在使用时采用以下提示词（Prompt）和负面提示词（Negative Prompt）：

P: best quality, masterpiece
NP: 3d, flat shading, flat color, retro style, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019, 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, artist name, inaccurate limb

高级用法

以下是一些具体的使用示例及参数设置：

示例一

(((best quality, masterpiece, 8k))), detailed anime style of 1girl sitting in room and reading book wearing school uniform and wavy detailed pink hair pink and detailed yellow eye yellow, smiling
Negative prompt: [[3d]], (((flat shading, flat color))), retro style, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019, 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, artist name, inaccurate limb
Steps: 25, Sampler: Euler a, CFG scale: 8, Seed: 2277801742, Size: 512x768, Model hash: 6d1729a039, Denoising strength: 0.75, Clip skip: 2, ENSD: 31337, Hires upscale: 1.5, Hires upscaler: Latent

示例二

(((best quality, masterpiece, 8k))), detailed anime style of anime 1girl bust shot sitting and dipping in river and wetty wearing white transparent onepiece dress with detailed wavy pink hair pink and hetailed yellow eye yellow, water splash in gorgeous scene secret garden
Negative prompt: [[[3d]]], (((flat shading, flat color))), retro style, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019, 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, artist name, inaccurate limb
Steps: 20, Sampler: DPM++ SDE Karras, CFG scale: 8, Seed: 1117106368, Size: 512x768, Model hash: 6d1729a039, Denoising strength: 0.7, Clip skip: 2, ENSD: 31337, Hires resize: 768x1152, Hires steps: 5, Hires upscaler: Latent

示例三

(((best quality, masterpiece))), detailed anime style of bunny girl bishoujo from front wearing intricate frill jirai kei bikini with detailed wavy pink hair pink and detailed yellow eye yellow and lying on the bed in (((glitter harajuku kawaii messy room with flower and candy)))
Negative prompt: 3d, (((flat shading, flat color))), retro style, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019, 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, artist name, inaccurate limb, eating
Steps: 50, Sampler: DPM++ SDE Karras, CFG scale: 5.5, Seed: 911018641, Size: 768x512, Model hash: 6d1729a039, Denoising strength: 0.2, Clip skip: 2, ENSD: 31337, Hires resize: 1152x768, Hires steps: 10, Hires upscaler: ESRGAN_4x

示例四

(((best quality, masterpiece))), detailed anime style of 1girl bishoujo full body standing and looking from viewer and wearing classical frill dress with cape with wavy detailed pink hair pink and detailed yellow hair yellow in scenic view british fantastic landscape with flowing and golden hour, dynamic pose
Negative prompt: [[[[3d]]]], (((flat shading, flat color))), retro style, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019, 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, artist name, inaccurate limb
Steps: 15, Sampler: DPM++ SDE Karras, CFG scale: 5.5, Seed: 2149903685, Size: 768x512, Model hash: 6d1729a039, Denoising strength: 0.75, Clip skip: 2, ENSD: 31337, Hires resize: 1152x768, Hires steps: 10, Hires upscaler: Latent

示例五

(((best quality, masterpiece, 8k))), detailed anime style of 1boy cowboy shot wearing samurai outfit with flat chest and fighting pose, fist, motion blur
Negative prompt: 3d, flat shading, flat color, retro style, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019, 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, artist name, inaccurate limb
Steps: 20, Sampler: Euler a, CFG scale: 8, Seed: 2136917906, Size: 512x768, Model hash: 6d1729a039, Denoising strength: 0.6, Clip skip: 2, ENSD: 31337, Hires resize: 768x1152, Hires steps: 20, Hires upscaler: Latent

示例六

(((best quality, masterpiece, 8k))), detailed photorealistic style of 1boy cowboy shot wearing mad max outfit with flat chest and fighting pose, fist, motion blur, abandoned city background
Negative prompt: (((flat shading, flat color))), retro style, 1980s, 1990s, 2000s, 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019, 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, artist name, inaccurate limb
Steps: 20, Sampler: Euler a, CFG scale: 8, Seed: 3787706619, Size: 768x512, Model hash: 6d1729a039, Denoising strength: 0.7, Clip skip: 2, ENSD: 31337, Hires resize: 1152x768, Hires steps: 5, Hires upscaler: Latent

🔧 技术细节

模型合并与训练步骤

以下，模型旁记载的符号串是Automatic1111 Webui提交哈希c98cb0f8ecc904666f47684e238dd022039ca16f时，模型选择时记载的ckpt的哈希值。

1. 差分合并：将Trinart Derrida与Dreamlike Diffusion 1.0进行差分合并。 | 插值方法 | 主模型 | 次模型 | 第三模型 | 合并名称 | | --- | --- | --- | --- | --- | | Add Difference @ 1.0 | DreamLike Diffusion 1.0(0aecbcfa2c) | TrinArt Characters v2 Derrida(42d3f359b0) | Stable Diffusion 1.4(fe4efff1e1) | DDD_pre1(d1ac03017b) |

2. 层次合并：用Dreamlike Photoreal 1.0对DDD_pre1的IN00~IN05进行层次合并编辑。 | 模型A | 模型B | 权重 | 基础alpha | 合并名称 | | --- | --- | --- | --- | --- | | DDD_pre1(d1ac03017b) | Dreamlike Photoreal 1.0(f403e4e2a5) | 0.45,0.45,0.4,0.35,0.3,0.25,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 | 0 | DDD_pre2(601ec74593) |

3. 微调训练：使用自行准备的其他Diffusion模型输出的素材图像对DDD_pre2进行训练。训练使用的服务/模型包括SD2.1、Novel AI、WD1.3/1.4、CoolJapan Diffusion 2.1、Dreamlike Photoreal 2.0，总数约30000张，加上翻转后的图像，学习率为5e - 6，训练60000步，生成的模型为DDD_pre3(4709475652)。

4. 加权平均合并：将DDD_pre3与DDD_pre2进行加权平均合并。 | 插值方法 | 主模型 | 次模型 | 合并名称 | | --- | --- | --- | --- | | Weighted Sum @ 0.5 | DDD_pre3(4709475652) | DDD_pre2(601ec74593) | DeDeDe(6d1729a039) |

模型变体

DeDeDe_ip2p_0.7_0.8.ckpt/DeDeDe_ip2p_0.7_1.0.ckpt

这是从Instruct pix2pix模型中提取任务向量并相加得到的模型，分别为DeDeDe 0.8/Instruct Pix2Pix 0.7和DeDeDe 1.0/Instruct Pix2Pix 0.7的大小。其遵循Instruct Pix2Pix继承的许可证： Copyright (c) 2023 Ren Nakayama Released under the MIT license https://huggingface.co/nakayama/DeDeDe/blob/main/MIT-License

DeDeDe_controlnet_.pth/DeDeDe_webui_controlnet_.safetensors

这是将DeDeDe与ControlNet中使用的模型合并的结果。具体方法请参考这里。

DeDeDeP

DeDeDeP是基于DeDeDe，使用Dreamlike Photoreal 1.0进行层次合并编辑的模型。与DeDeDe相比，其输出结果更偏向写实风格。

📄 许可证

本模型受Dreamlike Diffusion 1.0 / Dreamlike Photoreal 1.0的影响，适用上述模型的修正版CreativeML OpenRAIL - M许可证。以下是使用DeepL翻译的修正部分的日语译文，但在解释上优先使用英语。

• 您不能在有收入、有接受捐赠或计划有收入的网站/应用/其他平台上托管或使用此模型及其派生模型。如果您有此需求，请发邮件至contact@dreamlike.art。
• 您可以在商业和非商业网站/应用/其他平台上自由托管模型卡和文件（不涉及实际推理或微调）。请明确注明完整的模型名称（Dreamlike Diffusion 1.0 / Dreamlike Photoreal 1.0），并包含模型卡的链接（https://huggingface.co/dreamlike-art/dreamlike-diffusion-1.0 / https://huggingface.co/dreamlike-art/dreamlike-photoreal-1.0/ ）。
• 您可以在完全非商业的网站或应用等平台上自由托管模型及其派生模型（即不获得任何收益或捐赠）。请明确注明完整的模型名称（Dreamlike Diffusion 1.0 / Dreamlike Photoreal 1.0），并附上模型卡的链接（https://huggingface.co/dreamlike-art/dreamlike-diffusion-1.0 / https://huggingface.co/dreamlike-art/dreamlike-photoreal-1.0/ ）。
• 10人以下的团队可以自由将模型输出或模型派生输出用于商业目的。
• 您不能使用此模型故意创建或共享违法或有害的输出或内容。
• 对于您生成的输出，作者不主张任何权利。您可以自由使用它们，但需对其使用负责，不得违反许可证规定。
• 您可以重新分发权重。重新分发时，请务必注意，您必须与所有用户共享包含与许可证中相同使用限制的修正版CreativeML OpenRAIL - M副本（请完整并仔细阅读许可证）。完整的许可证内容请见：https://huggingface.co/nakayama/DeDeDe/blob/main/License.md

💡 使用建议

当您在SNS等平台上上传使用本模型生成的作品时，如果有标签等功能，希望您能加上#DeDeDeArt等标签，这样作者就能看到您的作品啦。