OneDiffusion提示词完全手册掌握text2image/multiview等10任务语法【免费下载链接】OneDiffusionOfficial implementation of OneDiffusion paper (CVPR 2025)项目地址: https://gitcode.com/gh_mirrors/one/OneDiffusionOneDiffusion是CVPR 2025论文的官方实现提供了强大的AI绘图功能支持text2image、multiview等10多种任务。本手册将帮助你快速掌握各种任务的提示词语法轻松生成高质量图像。一、基础提示词结构与优化技巧1.1 提示词基本格式OneDiffusion的提示词由任务令牌和描述文本两部分组成基本格式为[[任务令牌]] 详细描述文本例如[[text2image]] A beautiful sunset over the ocean with waves crashing on the shore1.2 提升图像质量的黄金法则 详细描述胜过简短提示模型在训练时使用了大量长文本描述因此详细的提示词能获得更好效果。建议包含以下元素主体特征形状、颜色、材质环境细节场景、光线、天气风格指定写实、卡通、油画等图1使用详细提示词生成的多样化图像展现了OneDiffusion对复杂文本的理解能力 分辨率设置指南text2image任务推荐768-1280像素高度/宽度需为16的倍数其他任务512像素左右效果最佳二、核心任务语法全解析2.1 文本生成图像text2image任务令牌[[text2image]]最佳实践使用20-50词的详细描述包含主体、动作、环境和风格信息。示例[[text2image]] A bipedal black cat wearing a huge oversized witch hat, a wizards robe, casting a spell in an enchanted forest. The scene is filled with fireflies and moss on surrounding rocks and trees图2text2image任务生成的多样化图像包括天使、机器人、风景等不同主题2.2 多视角生成multiview任务令牌[[multiview]]注意事项避免描述面部特征如直视镜头以防生成多脸问题。示例[[multiview]] A cat with orange and white fur sits on a round wooden table. The cat has striking green eyes and a pink nose. Its ears are perked up, and its tail is curled around its body. The background is blurred, showing a white wall, a wooden chair, and a wooden table with a white pot and green plant.图3multiview任务生成的3D场景多角度视图展现了同一物体的不同视角2.3 图像编辑image_editing任务令牌[[image_editing]]参数优化建议将引导尺度CFG设置为3-3.5避免过度饱和。示例[[image_editing]] add sunglasses [[image_editing]] change the cat to a white cat图4image_editing任务示例左图添加太阳镜右图将黑猫改为白猫2.4 ID定制faceid任务令牌[[faceid]]语法结构[[faceid]] [[img0]] 目标描述 [[img1]] 源图像1描述 [[img2]] 源图像2描述 [[img3]] 源图像3描述最佳实践源图像描述建议30-75词目标描述中加入部分源图像特征有助于保持身份一致性。示例[[faceid]] [[img0]] photo depict a female anime character with pink hair and blue eyes, sitting in a fine dining restaurant, black dress, smiling open mouth widely [[img1]] The photo depicts an anime-style cartoon character of a young woman with pink hair and blue eyes...图5ID定制任务中不同描述长度对结果的影响展示了身份特征的保持效果三、进阶任务与特殊令牌3.1 语义地图生成semanticmap2image任务令牌[[semanticmap2image]]特殊语法使用颜色掩码指定区域#颜色代码 颜色名称 mask: 物体描述示例[[semanticmap2image]] #00ffff Cyan mask: dragon #ff0000 red mask: bird #800080 purple mask: woman A woman in a red dress with gold floral patterns stands in a traditional Japanese-style building...3.2 主体驱动生成subject_driven任务令牌[[subject_driven]]语法结构[[subject_driven]] item: 主体名称 [[img0]] 目标描述 [[img1]] 源图像描述示例[[subject_driven]] item: cartoon dog [[img0]] a cartoon character resembling a dog, sitting on a beach... [[img1]] The photo features a cartoon character resembling a dog...3.3 深度引导生成depth2image任务令牌[[depth2image]]使用技巧可省略描述文本仅使用令牌[[depth2image]]示例[[depth2image]] The image depicts a futuristic astronaut standing on a rocky terrain with orange flowers. The astronaut is wearing a yellow suit with a helmet and is equipped with a backpack...四、任务令牌速查表任务名称任务令牌额外令牌文本生成图像[[text2image]]-图像去模糊[[deblurring]]-图像修复[[image_inpainting]]-边缘引导生成[[canny2image]]-深度引导生成[[depth2image]]-姿态引导生成[[pose2image]]-图像编辑[[image_editing]]-语义地图生成[[semanticmap2image]]#颜色代码 颜色名称 mask: 物体描述边界框生成[[boundingbox2image]]#颜色代码 颜色名称 boundingbox: 物体描述ID定制[[faceid]][[img0]]目标描述[[img1]]源图像描述多视角生成[[multiview]]-主体驱动生成[[subject_driven]]item: 主体名称[[img0]]目标描述[[img1]]源图像描述五、实用提示与常见问题5.1 负面提示词设置默认负面提示词无需手动添加monochrome, greyscale, low-res, 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 name5.2 推荐参数设置CFG值4.2文本生成3-3.5图像编辑步数50步采样器默认采样器即可获得良好效果5.3 快速开始指南克隆仓库git clone https://gitcode.com/gh_mirrors/one/OneDiffusion安装依赖pip install -r requirements.txt运行演示python gradio_demo.py在界面中输入提示词例如[[text2image]] your detailed prompt here点击生成图像按钮通过本手册你已经掌握了OneDiffusion所有核心任务的提示词语法。现在就开始创作探索AI绘图的无限可能吧无论是文本生成图像、多视角创作还是图像编辑OneDiffusion都能满足你的创意需求。【免费下载链接】OneDiffusionOfficial implementation of OneDiffusion paper (CVPR 2025)项目地址: https://gitcode.com/gh_mirrors/one/OneDiffusion创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考
