Giter VIP home page Giter VIP logo

comfyui-artgallery's Introduction

👋 Hi,我是 Zho !

中文 | English

trophy

ZHO-ZHO-ZHO%2FComfyUI-InstantID | Trendshift ZHO-ZHO-ZHO%2FComfyUI-Workflows-ZHO | Trendshift ZHO-ZHO-ZHO%2FComfyUI-PhotoMaker | Trendshift

🏛️ 职业

  • 职业建筑师 | 公共建筑
  • 罗杰斯✅福斯特❌ | 盖里✅扎哈❌ | 贝聿铭✅路易斯康❌

❣️ 兴趣

  • AIGC
  • 建筑设计&理论 | Archigram ✅ 结构主义✅
  • 艺术 | 蔡国强✅
  • 工业设计、交互设计

🤖 焦点

  • 目前独立从事 AIGC 研究与实践 | 图像✅ 视频✅ 3D✅ LLM✅
  • 论文解读 | 发展梳理 | 视频制作

🏗️重心

  • Stable Diffusion 生态 + ComfyUI:
    • ComfyPark 社区筹备中 | 安装与部署 | 系统教程 | 模块+模组 | 工作流设计 | 定制化UI
    • 编写、汉化或优化自定义节点
    • 设计工作流
    • 完成2000+节点测试
    • 未来推出ComfyUI的一个优化版本
  • AIGC 理论发展与梳理

🌟 技能

  • ChatGPT(哈哈哈)
  • Python

🔥 热门

  • Main 主库:

  • ComfyUI Assistant 智能助手:

    • ComfyUI Assistant:GPTs帮助创建或解释自定义节点或工作流,上榜 GPTs 全球对话数据第 165 名(12.29数据),目前已达1.7k!
  • 肖像大师(中文版):

  • 🆕UltraEdit 自动识别 + 图像编辑:

    • 🆕UltraEdit in ComfyUI: 基于 SD3 Medium 的 图像编辑模型,允许仅通过提示词实现指定内容的图像编辑,且能保持风格一致性,同时支持 全局编辑 和 区域蒙版编辑
  • SD3 API:

  • LLM & VLM 大型语言模型/视觉模型:

    • 🆕Qwen-2 in ComfyUI: 将 Qwen2 模型引入到 ComfyUI 中,目前支持 Qwen2-7B-Instruct 和 Qwen2-72B-Instruct 双模型,速度快且性能强,中文表现很不错,可用于 生成/补全提示词 或畅聊人生!
    • Phi-3-mini in ComfyUI: 将闪电般速度的 Phi-3-mini-4k 模型引入到 ComfyUI 中,生成/补全提示词,解数学题,畅聊人生!
    • Gemini in ComfyUI: 将 Gemini Pro 双模型引入到 ComfyUI 中,生成提示词、描述图像,也可与它畅聊人生!
    • QWen-VL in ComfyUI: 将目前最好的开源视觉模型 QWen-VL-Plus & Max 引入到 ComfyUI 中,超强细节、文字识别能力,支持单/多轮对话双模式!
  • 艺术画廊 | 提示词可视化:

    • ComfyUI ArtGallery | Prompt Visualization: 将近千种艺术提示词分类可视化,只需选择喜欢的图像 + 滑动选择权重,节点就会自动输出提示词,自由的在艺术世界翱翔吧!
  • 文字、图像合成 + 综合输入器 + 视频交互优化:

  • 物体检测 + 分割:

    • ComfyUI YoloWorld-EfficientSAM:利用全新的 YOLO-World 与 EfficientSAM 实现高效的对象检测 + 分割,支持选择指定蒙版单独输出,同时支持图像和视频
  • Background Remove 背景去除:

    • BiRefNet in ComfyUI:目前最好的开源可商用背景抠除模型,同时支持 图像和视频 处理
    • BRIA_RMBG 1.4 in ComfyUI:BRIA 开发的目前最好的背景去除模型,已支持批量处理(可去除视频背景)
  • 光栅动画:

  • Super-Resolution 超分/放大模型:

    • APISR in ComfyUI:专门用于动漫的超分模型,包含 2x 和 4x 双模型,速度飞快,效果很好
    • 🆕AuraSR in ComfyUI:基于 GigaGAN 的 4x 超分模型,速度快,效果还不错
  • 深度估计:

    • DepthFM IN ComfyUI:CompVis 推出的 高效 + 多功能 深度估计模型,同时支持 图像和视频 深度估计
  • 3D 生成:

    • 🆕ComfyUI Tripo-API ZHO:在 ComfyUI 中使用 Tripo-API 生成高质量 3D 模型!
    • ComfyUI TripoSR ZHO:TripoSR 在 ComfyUI 中的优化版,自带背景去除功能,修复原版黑色背景块bug,优化为按文件名保存 3D 模型
  • 人物特征保持/迁移:

    • ComfyUI PhotoMaker: 人物特征迁移与融合,支持单/多张参考图,轻松保持角色一致性!
    • ComfyUI InstantID: 仅需一张图就可实现高质量的角色保持!多种风格随心变!
    • ComfyUI PuLID: 人物特征迁移与融合新王者,支持单/多张参考图!
  • 其他:

📬 联系我

🔗 社交媒体

📅 未来计划

  • ComfyPark社区
  • 发布 ComfyUI 2400+ 节点测试报告
  • 开放精选期刊栏目(博客+订阅)
  • 推出 ComfyUI 的特殊优化版本

💡 支持我

comfyui-artgallery's People

Contributors

zho-zho-zho avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

comfyui-artgallery's Issues

Can't Install at all

I use stability Matrix

Cmd('git') failed due to: exit code(128)
cmdline: git clone -v --recursive --progress -- https://github.com/ZHO-ZHO-ZHO/ComfyUI-ArtGallery.git E:\Stabilty Matrix AI\Data\Packages\ComfyUI\custom_nodes\ComfyUI-ArtGallery

and if i use cmd directly on custom_nodes i get :

git clone https://github.com/ZHO-ZHO-ZHO/ComfyUI-ArtGallery.git
Cloning into 'ComfyUI-ArtGallery'...
remote: Enumerating objects: 1949, done.
remote: Counting objects: 100% (399/399), done.
remote: Compressing objects: 100% (386/386), done.
error: RPC failed; curl 92 HTTP/2 stream 5 was not closed cleanly: CANCEL (err 8)
error: 7956 bytes of body are still expected
fetch-pack: unexpected disconnect while reading sideband packet
fatal: early EOF
fatal: fetch-pack: invalid index-pack output

any ideas ?

【建议】浏览图片列表时希望能够实时显示图片

很棒的工作!

一点建议:希望类似pyssss的lora和模型加载节点,在浏览选择艺术家、风格等下拉图片列表时,能够随着鼠标移动实时显示对应的图片,这样更方便根据样例图片选择对应的艺术家等。

image

Error does not work

when launching comfyui this error appears:

C:\Users\Luna\Documents\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-ArtGallery../../web/extensions/core/uploadImage.js
Original code block not found.❌
File 'C:\Users\Luna
ArtGallery1
\Documents\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-ArtGallery../../folder_paths.py' updated successfully.✅
Original code block not found.❌

[建议] 项目容易克隆失败:预览图片能否再压缩一下,或者另外放置到云端网盘

项目克隆了好几次,太容易失败了,而且相对于国内,github的下载速度并不快
个人理解:
项目中提到 预览图片的作用一是可视化提示词(也提到这个是重点),二是输出参考图。所以个人觉得它不太需要有多么精细的画质,可以把它的画质降低或者大小再压缩一下,然后再放在项目中;或者是把预览图片与项目做分离,把它放在其他网盘中提供下载

下面是在终端上克隆项目的日志,失败了好几次,现在已经下载至少半个多小时,才下载 58% ,大小已经快 1个 G 了。太难了

PS D:\05Tools\Stable_Diffusion\Blender_ComfyUI\ComfyUI\custom_nodes> git clone https://github.com/ZHO-ZHO-ZHO/ComfyUI-ArtGallery.git
Cloning into 'ComfyUI-ArtGallery'...
remote: Enumerating objects: 1949, done.
remote: Counting objects: 100% (399/399), done.
remote: Compressing objects: 100% (386/386), done.
error: RPC failed; curl 92 HTTP/2 stream 5 was not closed cleanly: CANCEL (err 8)
error: 2427 bytes of body are still expected
fetch-pack: unexpected disconnect while reading sideband packet
fatal: early EOF
fatal: fetch-pack: invalid index-pack output
PS D:\05Tools\Stable_Diffusion\Blender_ComfyUI\ComfyUI\custom_nodes> git clone https://github.com/ZHO-ZHO-ZHO/ComfyUI-ArtGallery.git
Cloning into 'ComfyUI-ArtGallery'...
remote: Enumerating objects: 1949, done.
remote: Counting objects: 100% (399/399), done.
remote: Compressing objects: 100% (386/386), done.
error: RPC failed; curl 92 HTTP/2 stream 5 was not closed cleanly: CANCEL (err 8)
error: 7389 bytes of body are still expected
fetch-pack: unexpected disconnect while reading sideband packet
fatal: early EOF
fatal: fetch-pack: invalid index-pack output
PS D:\05Tools\Stable_Diffusion\Blender_ComfyUI\ComfyUI\custom_nodes> git clone https://github.com/ZHO-ZHO-ZHO/ComfyUI-ArtGallery.git
Cloning into 'ComfyUI-ArtGallery'...
remote: Enumerating objects: 1949, done.
remote: Counting objects: 100% (399/399), done.
remote: Compressing objects: 100% (386/386), done.
Receiving objects:  58% (1147/1949), 944.14 MiB | 404.00 KiB/s

'gbk' codec can't decode byte 0x80 in position 336: illegal multibyte sequence

E:\Blender_ComfyUI\ComfyUI\custom_nodes\ComfyUI-ArtGallery../../web/extensions/core/uploadImage.js
Traceback (most recent call last):
File "E:\Blender_ComfyUI\ComfyUI\nodes.py", line 1893, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in call_with_frames_removed
File "E:\Blender_ComfyUI\ComfyUI\custom_nodes\ComfyUI-ArtGallery_init
.py", line 56, in
modify_js_file(uploadimg_js_file_path, new_js_content)
File "E:\Blender_ComfyUI\ComfyUI\custom_nodes\ComfyUI-ArtGallery_init_.py", line 6, in modify_js_file
content = file.read()
UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 336: illegal multibyte sequence

Cannot import E:\Blender_ComfyUI\ComfyUI\custom_nodes\ComfyUI-ArtGallery module for custom nodes: 'gbk' codec can't decode byte 0x80 in position 336: illegal multibyte sequence

Import Failed - No Matter What I Do?

C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-ArtGallery../../web/extensions/core/uploadImage.js
Original code block not found.❌
File 'C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-ArtGallery../../folder_paths.py' updated successfully.✅
Traceback (most recent call last):
File "C:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1800, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 940, in exec_module
File "", line 241, in call_with_frames_removed
File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-ArtGallery_init
.py", line 256, in
modify_wedgets_js_file(wedgets_js_file_path, new_wedgets_js_content, new_wedgets_js_content_2)
File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-ArtGallery_init_.py", line 153, in modify_wedgets_js_file
file.write(content)
File "encodings\cp1252.py", line 19, in encode
UnicodeEncodeError: 'charmap' codec can't encode characters in position 6973-6981: character maps to

Cannot import C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-ArtGallery module for custom nodes: 'charmap' codec can't encode characters in position 6973-6981: character maps to
I have tried everything - I believe?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.