date
type
status
slug
summary
tags
category
icon
password
URL
I’ve open-sourced an AI bionic product generator~! 🤗 (Generates design concepts, descriptions, 2D images, and 3D models in one go using Chain-of-Thought!)

🌟3D-Bionic-Designer

➡️Link: https://github.com/shengyu-meng/3D-Bionic-Designer (Your stars are highly appreciated! 🥹)

🥰Key Features

💡Chain-of-Thought (CoT) driven 3D bionic designer, powered by ComfyUI backend + Gradio frontend.
💡Simply input a reference organism (name/image) and design target (e.g., table, chair, pavilion), and it generates corresponding bionic designs with descriptions, images, and 3D models.
💡The LLM/LVM first parses inputs and autonomously executes the workflow: "Design Concept" → "Visual Description" → "Prompt" → "2D Image" → "3D Model".
💡All computations use local open-source models - no API or internet required after installation.

🥰Use Cases

✅Bionic furniture/product/architectural concept generation
✅A practical example for integrating Gradio frontend with ComfyUI backend (ComfyUI's API docs are too brief...)
✅Customizable ComfyUI workflows (update node IDs in Gradio if modifying critical output nodes)
✅Learn CoT prompt engineering through real-world examples

🥰Next Steps

❓Find a low-cost cloud platform to deploy a public demo (Current full-machine rentals are too expensive, and serverless platforms struggle with dependency-heavy workflows – more research needed 🐶)

❤️Special Thanks

notion image
notion image
Thanks to CCS (ComfyUI Community Summit) for the invitation! This project was recently exhibited at the SOMSOC Gallery in Tokyo~!
 
相关文章
Microcosmic Universe
Lazy loaded image
Project Title: One and Three Objects, and An Attempt at Exhausting the Object
Lazy loaded image
One and three objects, and an attempt at exhausting the object
Lazy loaded image
How I Used AI to Create a Promotional Video for Xiaomi's Daniel Arsham Limited Edition Smartphone
Lazy loaded image
3D scene editing has entered the era of AI text interaction
Lazy loaded image
Works Series - Dimensional Recasting
Lazy loaded image
I have developed an open-source AI tool for generating 3D models from text, Dreamfields-3DA Book from the Sky
Loading...
Simon Shengyu Meng
Simon Shengyu Meng
AI artist driven by curiosity, cross-disciplinary researcher, PhD candidate, science communication blogger.
最新发布
Works Series - MicroCosmos
Mar 9, 2025
Microcosmic Universe
Mar 9, 2025
Project Title: One and Three Objects, and An Attempt at Exhausting the Object
Mar 7, 2025
A Book from the Sky
Mar 7, 2025
Works Series - Dimensional Recasting
Feb 9, 2025
One and three objects, and an attempt at exhausting the object
Feb 9, 2025
公告
--- About me ---
--- Contact Me ---
Design and Art Creation | AIGC Consultation and Training | Commercial Deployment