v1.2.4: 优化预设分类结构，提升用户体验
- 重新整理预设分类，合并相似类别，减少重复 - 将原11个分类优化为7个主要分类：核心编辑、图像合成、场景环境、摄影技术、人物变换、艺术风格、特殊效果 - 将视角变换类合并到摄影技术类，将花纹提取类合并到核心编辑类 - 将环境变换类合并到场景环境类，简化分类结构 - 优化预设顺序，保持万能编辑作为默认选项 - 提升预设分类的逻辑性和易用性 - 保持所有30个预设的完整功能不变 - 新增PRESET_CATEGORIES.md详细分类说明文档 - 更新README.md，添加新的分类说明和使用建议
This commit is contained in:
Cyber Dick Lang
@@ -0,0 +1,81 @@
|
||||
# ComfyUI-UniversalToolkit 预设分类说明
|
||||
|
||||
## 分类优化概述
|
||||
|
||||
经过优化，将原来的11个分类合并为7个主要分类，提升了分类的逻辑性和易用性。
|
||||
|
||||
## 新的分类结构
|
||||
|
||||
### 1. 核心编辑类 (2个预设)
|
||||
- **Universal Editor (万能编辑)** - 默认预设，支持精确的图像编辑指令转换
|
||||
- **Pattern Extraction (花纹提取)** - 从指定对象提取花纹或logo，转换为无缝平面纹理
|
||||
|
||||
### 2. 图像合成类 (2个预设)
|
||||
- **Context Deep Fusion (情境深度融合)** - 深度融合不同上下文的头部和身体
|
||||
- **Seamless Integration (无痕融合)** - 微调级别的图像合成，创造完美融合效果
|
||||
|
||||
### 3. 场景环境类 (5个预设)
|
||||
- **Scene Teleportation (场景传送)** - 将主体传送到完全不同的环境
|
||||
- **Season Change (季节变换)** - 改变场景的季节设定
|
||||
- **Fantasy World (幻想领域)** - 将场景转换为奇幻或科幻世界
|
||||
- **Furniture Removal (清空家具)** - 移除房间内的所有家具
|
||||
- **Interior Design (室内设计)** - 重新设计室内空间风格
|
||||
|
||||
### 4. 摄影技术类 (7个预设)
|
||||
- **Camera Movement (移动镜头)** - 戏剧性的镜头移动效果
|
||||
- **Relighting (重新布光)** - 完全改变图像的光照和氛围
|
||||
- **Camera Zoom (画面缩放)** - 有目的的缩放效果
|
||||
- **Professional Product Photography (专业产品图)** - 商业级产品摄影效果
|
||||
- **Tilt-Shift Miniature (微缩世界)** - 倾斜移轴微缩效果
|
||||
- **Reflection Addition (添加倒影)** - 添加反射表面增强构图
|
||||
- **Character Pose & Viewpoint Change (角色姿势视角变换)** - 改变角色视角保持特征一致
|
||||
|
||||
### 5. 人物变换类 (4个预设)
|
||||
- **Hair Style Change (更换发型)** - 完整的发型变换
|
||||
- **Bodybuilding Transformation (肌肉猛男化)** - 肌肉发达的体型变换
|
||||
- **Age Transformation (时光旅人)** - 年龄变换效果
|
||||
- **Fashion Makeover (衣橱改造)** - 完整的时尚改造
|
||||
|
||||
### 6. 艺术风格类 (6个预设)
|
||||
- **Image Colorization (图像上色)** - 黑白图像的艺术上色
|
||||
- **Cartoon/Anime Style (卡通漫画化)** - 卡通或动漫风格转换
|
||||
- **Artistic Style Imitation (艺术风格模仿)** - 著名艺术运动风格模仿
|
||||
- **Pixel Art (像素艺术)** - 像素艺术风格转换
|
||||
- **Pencil Sketch (铅笔手绘)** - 铅笔素描风格
|
||||
- **Oil Painting (油画风格)** - 油画风格转换
|
||||
|
||||
### 7. 特殊效果类 (4个预设)
|
||||
- **Material Transformation (材质置换)** - 将主体转换为不同材质
|
||||
- **Movie Poster (电影海报)** - 电影海报风格转换
|
||||
- **Technical Blueprint (蓝图视角)** - 技术蓝图风格
|
||||
- **Text Removal (移除文字)** - 移除图像中的文字
|
||||
|
||||
## 分类优化说明
|
||||
|
||||
### 合并的类别
|
||||
1. **视角变换类** → 合并到 **摄影技术类**
|
||||
- 理由：视角变换本质上是摄影技术的一种，与镜头移动、缩放等技术密切相关
|
||||
|
||||
2. **花纹提取类** → 合并到 **核心编辑类**
|
||||
- 理由：花纹提取是核心的图像编辑功能，与万能编辑同属基础编辑操作
|
||||
|
||||
3. **环境变换类** → 合并到 **场景环境类**
|
||||
- 理由：家具移除和室内设计都是环境变换的具体应用，逻辑上属于同一类别
|
||||
|
||||
### 优化效果
|
||||
- **减少分类数量**：从11个减少到7个，降低用户选择复杂度
|
||||
- **提升逻辑性**：相似功能的预设归类在一起，便于用户理解和使用
|
||||
- **保持完整性**：所有30个预设功能保持不变，只是重新组织分类
|
||||
- **优化用户体验**：万能编辑作为默认选项，花纹提取紧随其后，符合用户使用习惯
|
||||
|
||||
## 使用建议
|
||||
|
||||
1. **新手用户**：建议从"核心编辑类"开始，特别是"万能编辑"预设
|
||||
2. **图像合成需求**：使用"图像合成类"的预设
|
||||
3. **场景变换需求**：使用"场景环境类"的预设
|
||||
4. **摄影效果需求**：使用"摄影技术类"的预设
|
||||
5. **人物编辑需求**：使用"人物变换类"的预设
|
||||
6. **艺术创作需求**：使用"艺术风格类"的预设
|
||||
7. **特殊效果需求**：使用"特殊效果类"的预设
|
||||
|
||||
每个预设都支持`$user_prompt$`占位符，用户可以通过输入具体需求来获得个性化的指令生成。
|
||||
@@ -1,6 +1,6 @@
|
||||
# ComfyUI-UniversalToolkit
|
||||
|
||||
[](https://github.com/whmc76/ComfyUI-UniversalToolkit)
|
||||
[](https://github.com/whmc76/ComfyUI-UniversalToolkit)
|
||||
[](LICENSE)
|
||||
[](https://github.com/comfyanonymous/ComfyUI)
|
||||
|
||||
@@ -12,7 +12,7 @@
|
||||
- **🎵 音频处理**：音频加载、裁剪、重采样、增益调节等
|
||||
- **🎭 掩码操作**：掩码运算、填充、裁剪、预览等
|
||||
- **🛠️ 实用工具**：数学表达式、文本处理、显存清理、预设加载等
|
||||
- **📱 智能预设**：27种Kontext VLM系统预设，支持动态场景描述
|
||||
- **📱 智能预设**：30种Kontext VLM系统预设，支持动态场景描述
|
||||
- **🔧 模块化设计**：按功能分类，易于维护和扩展
|
||||
- **⚡ 高性能**：支持批量处理，优化内存使用
|
||||
|
||||
@@ -100,16 +100,53 @@ tqdm
|
||||
- **LoraInfo_UTK**：LoRA信息查询，获取CivitAI触发词、示例提示词、基础模型、元数据等信息
|
||||
|
||||
#### 预设系统
|
||||
- **LoadKontextPresets_UTK**：Kontext VLM系统预设，包含27种专业图像变换预设
|
||||
- 情境深度融合、无痕融合、场景传送
|
||||
- 移动镜头、重新布光、专业产品图
|
||||
- 画面缩放、图像上色、电影海报
|
||||
- 卡通漫画化、移除文字、更换发型
|
||||
- 肌肉猛男化、清空家具、室内设计
|
||||
- 季节变换、时光旅人、材质置换
|
||||
- 微缩世界、幻想领域、衣橱改造
|
||||
- 艺术风格模仿、蓝图视角、添加倒影
|
||||
- 像素艺术、铅笔手绘、油画风格
|
||||
- **LoadKontextPresets_UTK**：Kontext VLM系统预设，包含30种专业图像变换预设，分为7个主要分类：
|
||||
|
||||
**🎯 核心编辑类 (2个)**
|
||||
- Universal Editor (万能编辑) - 默认预设，精确的图像编辑指令转换
|
||||
- Pattern Extraction (花纹提取) - 从指定对象提取花纹或logo
|
||||
|
||||
**🖼️ 图像合成类 (2个)**
|
||||
- Context Deep Fusion (情境深度融合) - 深度融合不同上下文的头部和身体
|
||||
- Seamless Integration (无痕融合) - 微调级别的图像合成
|
||||
|
||||
**🌍 场景环境类 (5个)**
|
||||
- Scene Teleportation (场景传送) - 将主体传送到不同环境
|
||||
- Season Change (季节变换) - 改变场景的季节设定
|
||||
- Fantasy World (幻想领域) - 转换为奇幻或科幻世界
|
||||
- Furniture Removal (清空家具) - 移除房间内的所有家具
|
||||
- Interior Design (室内设计) - 重新设计室内空间风格
|
||||
|
||||
**📷 摄影技术类 (7个)**
|
||||
- Camera Movement (移动镜头) - 戏剧性的镜头移动效果
|
||||
- Relighting (重新布光) - 完全改变图像的光照和氛围
|
||||
- Camera Zoom (画面缩放) - 有目的的缩放效果
|
||||
- Professional Product Photography (专业产品图) - 商业级产品摄影效果
|
||||
- Tilt-Shift Miniature (微缩世界) - 倾斜移轴微缩效果
|
||||
- Reflection Addition (添加倒影) - 添加反射表面增强构图
|
||||
- Character Pose & Viewpoint Change (角色姿势视角变换) - 改变角色视角保持特征一致
|
||||
|
||||
**👤 人物变换类 (4个)**
|
||||
- Hair Style Change (更换发型) - 完整的发型变换
|
||||
- Bodybuilding Transformation (肌肉猛男化) - 肌肉发达的体型变换
|
||||
- Age Transformation (时光旅人) - 年龄变换效果
|
||||
- Fashion Makeover (衣橱改造) - 完整的时尚改造
|
||||
|
||||
**🎨 艺术风格类 (6个)**
|
||||
- Image Colorization (图像上色) - 黑白图像的艺术上色
|
||||
- Cartoon/Anime Style (卡通漫画化) - 卡通或动漫风格转换
|
||||
- Artistic Style Imitation (艺术风格模仿) - 著名艺术运动风格模仿
|
||||
- Pixel Art (像素艺术) - 像素艺术风格转换
|
||||
- Pencil Sketch (铅笔手绘) - 铅笔素描风格
|
||||
- Oil Painting (油画风格) - 油画风格转换
|
||||
|
||||
**✨ 特殊效果类 (4个)**
|
||||
- Material Transformation (材质置换) - 将主体转换为不同材质
|
||||
- Movie Poster (电影海报) - 电影海报风格转换
|
||||
- Technical Blueprint (蓝图视角) - 技术蓝图风格
|
||||
- Text Removal (移除文字) - 移除图像中的文字
|
||||
|
||||
> 📖 **详细分类说明**：查看 [PRESET_CATEGORIES.md](PRESET_CATEGORIES.md) 了解完整的分类优化说明和使用建议。
|
||||
|
||||
## 🚀 使用示例
|
||||
|
||||
@@ -139,7 +176,38 @@ AudioCropProcess_UTK
|
||||
|
||||
## 📋 版本历史
|
||||
|
||||
### v1.2.0 (最新)
|
||||
### v1.2.4 (最新)
|
||||
- 优化预设分类结构，提升用户体验
|
||||
- 将原11个分类优化为7个主要分类：核心编辑、图像合成、场景环境、摄影技术、人物变换、艺术风格、特殊效果
|
||||
- 合并相似类别，减少重复，提升分类逻辑性
|
||||
- 保持所有30个预设的完整功能不变
|
||||
- 优化预设顺序，万能编辑作为默认选项
|
||||
|
||||
### v1.2.3
|
||||
- 新增花纹提取预设和优化用户体验
|
||||
- 添加Pattern Extraction (花纹提取)预设，支持指定提取对象
|
||||
- 将Universal Editor (万能编辑)预设移到最前面作为默认选项
|
||||
- 优化预设顺序，提升用户使用体验
|
||||
- 支持从任意对象中提取花纹、logo、图案等
|
||||
- 完全支持$user_prompt$占位符替换机制
|
||||
- 预设总数达到30个，覆盖各种图像处理需求
|
||||
|
||||
### v1.2.2
|
||||
- 新增万能编辑预设功能
|
||||
- 添加Universal Editor (万能编辑)预设，支持精确的图像编辑指令转换
|
||||
- 基于Kontext格式和Flux模型的编辑指令生成
|
||||
- 支持人物、物体、背景、风格、文本等多种编辑类型
|
||||
- 严格遵循9条编辑规则，确保视觉一致性和精确性
|
||||
- 完全支持$user_prompt$占位符替换机制
|
||||
- 优化预设指令结构，移除重复的英文输出要求
|
||||
|
||||
### v1.2.1
|
||||
- 升级LoadKontextPresets_UTK节点功能
|
||||
- 新增用户提示输入参数，支持动态场景描述
|
||||
- 为所有27个预设添加$user_prompt$占位符
|
||||
- 智能占位符替换，提升VLM模型生成指令的针对性
|
||||
|
||||
### v1.2.0
|
||||
- 全面更新README文档，提供详细的功能介绍和使用指南
|
||||
- 优化项目结构和文档组织
|
||||
- 完善节点功能说明和分类
|
||||
|
||||
+11
-1
@@ -8,13 +8,23 @@ A comprehensive toolkit for ComfyUI that provides various utility nodes for imag
|
||||
:license: MIT, see LICENSE for more details.
|
||||
"""
|
||||
|
||||
__version__ = "1.2.3"
|
||||
__version__ = "1.2.4"
|
||||
__author__ = "CyberDickLang"
|
||||
__email__ = "286878701@qq.com"
|
||||
__url__ = "https://github.com/whmc76"
|
||||
|
||||
# 更新日志
|
||||
CHANGELOG = {
|
||||
"1.2.4": [
|
||||
"优化预设分类结构，提升用户体验：",
|
||||
"- 重新整理预设分类，合并相似类别，减少重复",
|
||||
"- 将原11个分类优化为7个主要分类：核心编辑、图像合成、场景环境、摄影技术、人物变换、艺术风格、特殊效果",
|
||||
"- 将视角变换类合并到摄影技术类，将花纹提取类合并到核心编辑类",
|
||||
"- 将环境变换类合并到场景环境类，简化分类结构",
|
||||
"- 优化预设顺序，保持万能编辑作为默认选项",
|
||||
"- 提升预设分类的逻辑性和易用性",
|
||||
"- 保持所有30个预设的完整功能不变",
|
||||
],
|
||||
"1.2.3": [
|
||||
"新增花纹提取预设和优化用户体验：",
|
||||
"- 添加Pattern Extraction (花纹提取)预设，支持指定提取对象",
|
||||
|
||||
@@ -5,12 +5,16 @@ class LoadKontextPresets_UTK:
|
||||
data = {
|
||||
"prefix": "You are a creative prompt engineer. Your mission is to analyze the provided image and generate exactly 1 distinct image transformation *instructions*. IMPORTANT: You must respond in English only.",
|
||||
"presets": [
|
||||
# === 万能编辑类 ===
|
||||
# === 核心编辑类 ===
|
||||
{
|
||||
"name": "Universal Editor (万能编辑)",
|
||||
"brief": "You are a task-aware prompt translator for single-image editing using the Kontext format with the Flux model. Your role is to convert the user's natural language instruction into a clean, precise, and visually consistent image editing directive. Follow these strict rules: 1. Do not describe the original image - assume the model sees it. 2. Only describe what needs to change using clear verbs like replace, add, remove, insert, transform into, convert to. 3. Always state what must remain unchanged: for persons preserve facial features, expression, pose, hairstyle, skin tone, body proportion, clothing texture, and lighting; for objects preserve shape, scale, material, texture, surface details, lighting, reflections, and shadow behavior. 4. For background changes describe only the new scene, keep the main subject in exact same position, scale, lighting, and focus, ensure visual integration. 5. For style transfer name the visual style specifically and maintain original composition. 6. For text editing use quotes for target text and specify font retention if needed. 7. For composite edits ensure product stays visually dominant and unchanged with seamless integration. 8. Break complex changes into clear simple steps. 9. Output must be one paragraph in natural English starting with change description, including what to preserve, ending with visual consistency requirements. Based on the user's specific request: $user_prompt$, provide a precise editing instruction that follows these guidelines.",
|
||||
},
|
||||
# === 拼接/合成图片处理类 ===
|
||||
{
|
||||
"name": "Pattern Extraction (花纹提取)",
|
||||
"brief": "Extract the visible pattern or logo from the $user_prompt$ in the image and convert it into a seamless flat texture. Remove all lighting, shading, wrinkles, folds, and perspective distortions. Ensure the output is a clean, high-resolution top-down view of the pattern with no character, background, or surrounding elements included. Preserve the original colors, fine details, and relative scale of the pattern as seen on the specified object. The extraction should isolate the pattern completely, eliminating any 3D effects, shadows, or environmental influences while maintaining the authentic visual characteristics and color palette of the original design.",
|
||||
},
|
||||
# === 图像合成类 ===
|
||||
{
|
||||
"name": "Context Deep Fusion (情境深度融合)",
|
||||
"brief": "The provided image is a composite with a head and body from drastically different contexts (lighting, style, condition). Your mission is to generate instructions for a complete narrative and physical transformation of the head to flawlessly match the body and scene. The instructions must guide the AI to: 1. **Cinematic Re-Lighting**: Describe in vivid detail the scene's light sources (color, direction, hardness) and how this light should sculpt the head's features with new, appropriate shadows and highlights. 2. **Contextual Storytelling**: Instruct to add physical evidence of the scene's story onto the head, such as grime from a battle, sweat from exertion, or rain droplets from a storm. 3. **Color Grading Unification**: Detail how to apply the scene's specific color grade (e.g., cool desaturated tones, warm golden hour hues) to the head. 4. **Asset & Hair Adaptation**: Command the modification or removal of out-of-place elements (like clean jewelry in a gritty scene) and the restyling of the hair to fit the environment (e.g., messy, windblown, wet). 5. **Flawless Final Integration**: As the final step, describe the process of blending the neckline to be completely invisible, ensuring a uniform film grain and texture across the entire person.",
|
||||
@@ -19,7 +23,7 @@ class LoadKontextPresets_UTK:
|
||||
"name": "Seamless Integration (无痕融合)",
|
||||
"brief": "This image is a composite with minor inconsistencies between the head and body. Your task is to generate instructions for a subtle but master-level integration. Focus on creating a photorealistic and utterly convincing final image. The instructions should detail: 1. **Micro-Lighting Adjustment**: Fine-tune the lighting and shadows around the neck and jawline to create a perfect match. 2. **Skin Tone & Texture Unification**: Describe the process of unifying the skin tones for a seamless look, and more importantly, harmonizing the micro-textures like pores, fine hairs, and film grain across the blended area. 3. **Edge Blending Perfection**: Detail how to create an invisible transition at the neckline, making it appear as if it was never separate.",
|
||||
},
|
||||
# === 场景变换类 ===
|
||||
# === 场景环境类 ===
|
||||
{
|
||||
"name": "Scene Teleportation (场景传送)",
|
||||
"brief": "Imagine the main subject of the image is suddenly teleported to a completely different and unexpected environment, while maintaining their exact pose. Based on the user's specific request: $user_prompt$, describe this new, richly detailed scene. The instruction must detail how the new environment's lighting and atmosphere should realistically affect the subject, including any necessary adjustments to clothing, accessories, or physical appearance to match the new setting.",
|
||||
@@ -32,6 +36,14 @@ class LoadKontextPresets_UTK:
|
||||
"name": "Fantasy World (幻想领域)",
|
||||
"brief": "Transport the entire scene and its subject into a specific, richly detailed fantasy or sci-fi universe. Based on the user's specific request: $user_prompt$, describe the complete aesthetic overhaul. Replace modern elements with fantasy/sci-fi equivalents, transform clothing and accessories to match the new universe, and ensure the subject's appearance fits the magical or futuristic setting.",
|
||||
},
|
||||
{
|
||||
"name": "Furniture Removal (清空家具)",
|
||||
"brief": "Imagine the room in the image has been completely emptied for renovation. Based on the user's specific request: $user_prompt$, describe the furniture removal process. Specify what items need to be removed, how to realistically recreate the empty surfaces, and any necessary adjustments to lighting or architectural details to maintain the room's integrity.",
|
||||
},
|
||||
{
|
||||
"name": "Interior Design (室内设计)",
|
||||
"brief": "Redesign this space in a specific, evocative style. Based on the user's specific request: $user_prompt$, describe the complete interior redesign. Specify furniture, color schemes, lighting, decor elements, and overall aesthetic while keeping the room's core structure intact. Create a cohesive design that reflects the desired style and mood.",
|
||||
},
|
||||
# === 摄影技术类 ===
|
||||
{
|
||||
"name": "Camera Movement (移动镜头)",
|
||||
@@ -57,6 +69,10 @@ class LoadKontextPresets_UTK:
|
||||
"name": "Reflection Addition (添加倒影)",
|
||||
"brief": "Introduce a new, reflective surface into the scene to create a more dynamic composition. Based on the user's specific request: $user_prompt$, describe the reflective surface and its placement. Specify the type of reflection (mirror-like, water, glass, etc.), its quality and distortion, and how it enhances the overall composition and mood of the scene.",
|
||||
},
|
||||
{
|
||||
"name": "Character Pose & Viewpoint Change (角色姿势视角变换)",
|
||||
"brief": "Generate a $user_prompt$ view of the same character, keeping all visual features identical, including facial structure, hairstyle, expression, body proportions, clothing design, and rendering style. Only change the viewpoint angle. Ensure that lighting direction, shading, and character identity remain consistent with the original image, with no alterations to details other than the perspective. The instruction must specify the exact camera angle and position while maintaining perfect character consistency.",
|
||||
},
|
||||
# === 人物变换类 ===
|
||||
{
|
||||
"name": "Hair Style Change (更换发型)",
|
||||
@@ -74,15 +90,6 @@ class LoadKontextPresets_UTK:
|
||||
"name": "Fashion Makeover (衣橱改造)",
|
||||
"brief": "Give the subject a complete fashion makeover into a specific style. Based on the user's specific request: $user_prompt$, describe the entire outfit transformation. Specify clothing items, accessories, styling details, and how this fashion change reflects the desired aesthetic or persona. Include any necessary adjustments to hair or makeup to complement the new look.",
|
||||
},
|
||||
# === 环境变换类 ===
|
||||
{
|
||||
"name": "Furniture Removal (清空家具)",
|
||||
"brief": "Imagine the room in the image has been completely emptied for renovation. Based on the user's specific request: $user_prompt$, describe the furniture removal process. Specify what items need to be removed, how to realistically recreate the empty surfaces, and any necessary adjustments to lighting or architectural details to maintain the room's integrity.",
|
||||
},
|
||||
{
|
||||
"name": "Interior Design (室内设计)",
|
||||
"brief": "Redesign this space in a specific, evocative style. Based on the user's specific request: $user_prompt$, describe the complete interior redesign. Specify furniture, color schemes, lighting, decor elements, and overall aesthetic while keeping the room's core structure intact. Create a cohesive design that reflects the desired style and mood.",
|
||||
},
|
||||
# === 艺术风格类 ===
|
||||
{
|
||||
"name": "Image Colorization (图像上色)",
|
||||
@@ -126,16 +133,6 @@ class LoadKontextPresets_UTK:
|
||||
"name": "Text Removal (移除文字)",
|
||||
"brief": "Remove all text from the image as a meticulous restoration project. Based on the user's specific request: $user_prompt$, describe the text removal process. Specify which text elements need to be removed, how to reconstruct underlying surfaces, and any restoration techniques needed to create a seamless, text-free image.",
|
||||
},
|
||||
# === 视角变换类 ===
|
||||
{
|
||||
"name": "Character Pose & Viewpoint Change (角色姿势视角变换)",
|
||||
"brief": "Generate a $user_prompt$ view of the same character, keeping all visual features identical, including facial structure, hairstyle, expression, body proportions, clothing design, and rendering style. Only change the viewpoint angle. Ensure that lighting direction, shading, and character identity remain consistent with the original image, with no alterations to details other than the perspective. The instruction must specify the exact camera angle and position while maintaining perfect character consistency.",
|
||||
},
|
||||
# === 花纹提取类 ===
|
||||
{
|
||||
"name": "Pattern Extraction (花纹提取)",
|
||||
"brief": "Extract the visible pattern or logo from the $user_prompt$ in the image and convert it into a seamless flat texture. Remove all lighting, shading, wrinkles, folds, and perspective distortions. Ensure the output is a clean, high-resolution top-down view of the pattern with no character, background, or surrounding elements included. Preserve the original colors, fine details, and relative scale of the pattern as seen on the specified object. The extraction should isolate the pattern completely, eliminating any 3D effects, shadows, or environmental influences while maintaining the authentic visual characteristics and color palette of the original design.",
|
||||
},
|
||||
],
|
||||
"suffix": "Your response must consist of concise instruction ready for the image editing AI. Do not add any conversational text, explanations, or deviations; only the instructions.",
|
||||
}
|
||||
|
||||
+1
-1
@@ -1,7 +1,7 @@
|
||||
[project]
|
||||
name = "universaltoolkit"
|
||||
description = "A comprehensive toolkit based on ComfyUI, providing image, mask, audio, and tools nodes, fully modular and v3 compatible."
|
||||
version = "1.2.3"
|
||||
version = "1.2.4"
|
||||
license = {file = "LICENSE"}
|
||||
dependencies = [
|
||||
"torch",
|
||||
|
||||
Reference in New Issue
Block a user