🏛️ Profession:
- Architect | Public Buildings
- Rogers ✅ Foster ❌ | Gehry ✅ Zaha ❌ | I.M.Pei ✅ Louis Kahn ❌
❣️ Interests:
- AIGC
- Architect & Theory | Archigram ✅ Structuralism ✅
- Art | Cai Guo-Qiang ✅
- Industrial Design, Interaction Design
🤖 Focus:
- Currently working independently on AIGC research and practice | Image ✅ Video ✅ 3D ✅ LLM ✅
- Paper Interpretation | Development Summarization | Video Production
🏗️ Main Focus:
- Stable Diffusion Ecosystem + ComfyUI:
- Preparing ComfyPark Community | Installation and Deployment | System Tutorials | Modules + Mods | Workflow Design | Customized UI
- Writing, translating, or optimizing custom nodes
- Designing workflows
- Completed testing of 2000+ nodes
- Future release of an optimized version of ComfyUI
- AIGC Theory Development and Summarization
🌟 Skills:
- ChatGPT (haha)
- Python
🔥 Hot:
- ComfyUI Workflows ZHO: My ComfyUI workflows collection
- 简体中文版 ComfyUI: Main repository, complete work content, and timeline
- ComfyUI Assistant：GPTs to help create or explain custom nodes or workflows, TOP 165 (12.29)
- ComfyUI Portrait Master 简体中文版: Character portrait prompt generation module
- Stable Diffusion 3 API ComfyUI: Using SD3 via API
- ComfyUI PuLID（diffusers）: Unofficial implementation of PuLID（diffusers） for ComfyUI
- Gemini in ComfyUI: Gemini Pro in ComfyUI
- QWen-VL in ComfyUI: QWen-VL-Plus & Max in ComfyUI
- ComfyUI ArtGallery | Prompt Visualization: 1000+ prompt of art, Prompt Visualization
- APISR in ComfyUI: Super-resolution model for anime
- BiRefNet in ComfyUI: Background removal model, both image and video processing, commercially available
- BRIA_RMBG 1.4 in ComfyUI：Background removal model by BRIA AI, both image and video processing, non-commercially
- ComfyUI YoloWorld-EfficientSAM：Efficient object detection + segmentation with YOLO-World and EfficientSAM, supporting the option to output specified masks separately, for both image and video
- DepthFM IN ComfyUI：Efficient + versatile depth estimation models introduced by CompVis, supporting depth estimation for both image and video
- ComfyUI TripoSR ZHO：Optimized version of TripoSR in ComfyUI, with built-in background removal functionality, fixing the original black background block bug, and optimizing for saving 3D models by file name
- ComfyUI PhotoMaker: Character feature migration and fusion, supporting single/multiple reference images, effortlessly maintaining character consistency!
- ComfyUI InstantID: Achieve high-quality character preservation with just one image! Easily switch between multiple styles!
- ComfyUI Text_+ Image：ComfyUI node for converting text to images, also compatible with generating subtitles or frame counts for videos
- ComfyUI Selector + CoInput Multilingual：CoInput: efficient integration + conducive to reuse + simplified interface + bilingual (Chinese and English) + avoids the drawbacks of repeated loading of efficiency-nodes
- ComfyUI SegMoE：MoE for SD
- ComfyUI PixArt-alpha Diffusers：PixArt-alpha-Diffusers
- Stable Video Diffusion in ComfyUI：Workflows for SVD
- ComfyUI I2VGenXL：I2VGenXL
- ComfyUI Differential_Diffusion Workflows：Workflows for Differential Diffusion
📬 Contact Me:
- Email: [email protected]
- QQ Group: 839821928
🔗 Social Media:
- Twitter: My Twitter
- Bilibili: My Bilibili Homepage
- Red: My Red Homepage
📅 Future Plans:
- ComfyPark Community
- Publishing ComfyUI 2400+ Node Test Report
- Opening a curated journal section (blog + subscription)
- Releasing a special optimized version of ComfyUI
💡 Support Me:
- Bilibili: Support me on Bilibili
- Aifadian: Support me