README.md · sharaborin/AIEXX_GENAI_IMAGE_TO

AIEXX_GENAI_IMAGE_TO_3D / README.md

sharaborin

Duplicate from AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D

65c834a 17 days ago

preview code

Raw

History Blame Contribute Delete

12.2 kB

	---
	license: apache-2.0
	language:
	- pt
	- en
	base_model:
	- stabilityai/stable-diffusion-1-5
	pipeline_tag: image-to-3d
	tags:
	- text-to-3d
	- image-to-3d
	- 3d-generation
	- 3d-reconstruction
	- stable-diffusion
	- triposr
	- comfyui
	- mesh-generation
	- gpu-optimized
	- nvidia
	- pytorch
	library_name: pytorch
	metrics:
	- inference_time
	- vram_usage
	---

	<div align="center">

	<table>
	<tr>
	<td align="center">

	```
	█████╗ ██╗███████╗██╗ ██╗██╗ ██╗
	██╔══██╗██║██╔════╝╚██╗██╔╝╚██╗██╔╝
	███████║██║█████╗ ╚███╔╝ ╚███╔╝
	██╔══██║██║██╔══╝ ██╔██╗ ██╔██╗
	██║ ██║██║███████╗██╔╝ ██╗██╔╝ ██╗
	╚═╝ ╚═╝╚═╝╚══════╝╚═╝ ╚═╝╚═╝ ╚═╝
	```

	</td>
	</tr>
	</table>

	# AIEXX GenAI Image to 3D

	### 🚀 Enterprise-Grade AI-Powered 3D Model Generation System
	Transform Text & Images into Production-Ready 3D Assets in Seconds

	---

	[![Version](https://img.shields.io/badge/version-1.0.0-blue.svg?style=for-the-badge&logo=semantic-release)](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/releases)
	[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-green.svg?style=for-the-badge)](https://opensource.org/licenses/Apache-2.0)
	[![Python](https://img.shields.io/badge/Python-3.11.9-3776AB?style=for-the-badge&logo=python&logoColor=white)](https://www.python.org/)
	[![PyTorch](https://img.shields.io/badge/PyTorch-2.7.0-EE4C2C?style=for-the-badge&logo=pytorch&logoColor=white)](https://pytorch.org/)
	[![CUDA](https://img.shields.io/badge/CUDA-12.8-76B900?style=for-the-badge&logo=nvidia&logoColor=white)](https://developer.nvidia.com/cuda-toolkit)

	[![GPU Optimized](https://img.shields.io/badge/GPU-RTX%205060%20Optimized-76B900.svg?style=for-the-badge&logo=nvidia)](https://www.nvidia.com/)
	[![ComfyUI](https://img.shields.io/badge/ComfyUI-Latest-orange.svg?style=for-the-badge)](https://github.com/comfyanonymous/ComfyUI)
	[![Stable Diffusion](https://img.shields.io/badge/Stable%20Diffusion-1.5-blueviolet?style=for-the-badge)](https://huggingface.co/)
	[![Build Status](https://img.shields.io/badge/build-passing-brightgreen.svg?style=for-the-badge)](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D)

	[![Stars](https://img.shields.io/github/stars/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D?style=social)](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/stargazers)
	[![Forks](https://img.shields.io/github/forks/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D?style=social)](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/network/members)
	[![Issues](https://img.shields.io/github/issues/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D?style=social&logo=github)](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/issues)

	---

	[🚀 Quick Start](#-quick-start) •
	[📖 Documentation](#-documentation) •
	[🎨 Workflows](#-workflows) •
	[⚙️ Tech Stack](#%EF%B8%8F-technology-stack) •
	[📊 Performance](#-performance-benchmarks) •
	[🤝 Contributing](#-contributing)

	</div>

	---

	## 🌟 Overview

	AIEXX GenAI Image to 3D is a professional, GPU-accelerated AI system for generating high-quality 3D models from text prompts or 2D images. Built on cutting-edge deep learning technologies, it delivers production-ready 3D assets in seconds.

	### 🎉 NEW: Standalone Image-to-3D System

	Transform any image into a 3D model locally - no compilation required!

	We've integrated TripoSR directly into the project with a custom implementation that works without pytorch3d. Simply drag and drop an image onto the launcher!

	```batch
	# Convert any image to 3D in seconds:
	AIEXX_IMAGE_TO_3D.bat your_photo.png
	# Output formats: OBJ, GLB, STL, PLY
	# Processing time: 30-70 seconds
	# Works 100% offline after first download
	```

	✅ Features:
	- 🚀 No compilation needed (pure Python)
	- 🗼️ Drag-and-drop interface
	- 💻 Full GPU acceleration (RTX 5060)
	- 🔐 100% local processing (privacy)
	- ⚡ Professional quality output

	📖 See [COMO_USAR_IMAGE_TO_3D.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/COMO_USAR_IMAGE_TO_3D.md) for complete guide

	### ✨ Key Features

	```
	🎯 TEXT-TO-3D GENERATION
	├─ Natural language prompts to 3D models
	├─ Stable Diffusion 1.5 integration
	├─ Advanced negative prompting
	└─ 20-60 seconds per model

	🗼️ IMAGE-TO-3D CONVERSION
	├─ Single image to full 3D mesh
	├─ Multi-view reconstruction support
	├─ Automated texture generation
	└─ 15-30 seconds processing time

	⚡ GPU ACCELERATION
	├─ NVIDIA RTX 5060 optimized
	├─ CUDA 12.8 + cuDNN integration
	├─ BF16 mixed precision training
	├─ Flash Attention v2 support
	└─ PyTorch 2.7.0 performance mode

	🎎 PROFESSIONAL OUTPUT
	├─ GLB/GLTF format export
	├─ PBR material support
	├─ Configurable mesh resolution
	└─ Blender/Unity/Unreal ready
	```

	---

	## 🚀 Quick Start

	### Prerequisites

	\| Component \| Requirement \| Status \|
	\|-----------\|------------\|--------\|
	\| OS \| Windows 10/11 (64-bit) \| ✅ \|
	\| GPU \| NVIDIA RTX 5060 (8GB VRAM) \| ✅ \|
	\| RAM \| 16GB minimum, 32GB recommended \| ✅ \|
	\| Storage \| ~55GB free space \| ✅ \|
	\| Python \| 3.11.9 \| ✅ \|

	### Installation

	#### Option 1: One-Click Automated Installation (⭐ EASIEST - Recommended)

	```batch
	# 1. Clone the repository
	git clone https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D.git
	cd AIEXX_GENAI_IMAGE_TO_3D

	# 2. Run the automated installer
	0-INSTALL_ALL_AUTOMATED.bat

	# That's it! The installer will:
	# ✅ Check system requirements
	# ✅ Install all dependencies automatically
	# ✅ Handle restart (run again after restart)
	# ✅ Download all models
	# ✅ Launch the system when done
	```

	Features:
	- ✨ Single command installation
	- 🔄 Auto-resume after restart
	- 🛡️ Error handling and recovery
	- 📊 Progress tracking with checkpoints
	- 💡 Clear instructions at each step

	See [INSTALACAO_AUTOMATIZADA.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/INSTALACAO_AUTOMATIZADA.md) for complete documentation.

	#### Option 2: Step-by-Step Installation (Advanced Users)

	```batch
	# 1. Clone the repository
	git clone https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D.git
	cd AIEXX_GENAI_IMAGE_TO_3D

	# 2. Install Visual Studio Build Tools (⚠️ RESTART after this!)
	1-INSTALL_VS_BUILDTOOLS_WINGET.bat

	# 3. Setup Python environment and dependencies
	2-FIX_VENV_AND_INSTALL_TORCH_SCATTER.bat

	# 4. Install ComfyUI 3D Pack
	3-RUN_INSTALL_3DPACK.bat

	# 5. Download AI models
	4-DOWNLOAD_3D_MODELS.bat

	# 6. (Optional) Download Stable Diffusion models
	5-SETUP_SD_MODELS.bat

	# 7. Launch the system
	6-START_AIEXX.bat
	```

	#### Option 3: Manual Setup

	See [INSTALLATION.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/INSTALLATION.md) for detailed manual installation instructions.

	### First Run

	1. Start the System
	```batch
	6-START_AIEXX.bat
	```

	2. Access Web Interface
	- Open browser: http://localhost:8188

	3. Load a Workflow
	- Click "Load" → Select from `workflows/3d/`
	- Recommended first workflow: `03_triposr_single_image_to_mesh.json`

	4. Generate Your First 3D Model
	- Upload an image or enter a text prompt
	- Click "Queue Prompt"
	- Wait ~20-60 seconds
	- Download your `.glb` file from `ComfyUI/output/`

	> 📋 Note: See [ORDEM_DE_INSTALACAO.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/ORDEM_DE_INSTALACAO.md) for complete installation order and troubleshooting.

	---

	## 📖 Documentation

	\| Document \| Description \|
	\|----------\|-------------\|
	\| [📋 ORDEM_DE_INSTALACAO.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/ORDEM_DE_INSTALACAO.md) \| Installation order and numbered scripts \|
	\| [📘 COMO_USAR.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/COMO_USAR.md) \| Complete usage guide (Portuguese) \|
	\| [🚀 QUICK_START_GUIDE.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/QUICK_START_GUIDE.md) \| Quick start guide \|
	\| [🔧 INSTALLATION.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/INSTALLATION.md) \| Detailed installation guide \|
	\| [📋 README_NEXT_STEPS.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/README_NEXT_STEPS.md) \| Next steps after installation \|
	\| [⚙️ SETUP_COMPLETE_3D_SYSTEM.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/SETUP_COMPLETE_3D_SYSTEM.md) \| Complete system setup \|
	\| [🚀 RELEASE_GUIDE.md](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/blob/main/RELEASE_GUIDE.md) \| Release and versioning guide \|

	---

	## 🎨 Workflows

	### Available Workflows

	<table>
	<tr>
	<td width="33%">

	#### 🟢 Basic - TripoSR
	`03_triposr_single_image_to_mesh.json`

	Pipeline:
	```
	Image > TripoSR > GLB
	```

	Specs:
	- Time: ~15-30s
	- VRAM: 3-4GB
	- Best for: Quick prototypes

	</td>
	<td width="33%">

	#### 🔵 Intermediate - Prompt to 3D
	`basic/AIEXX_prompt_to_3d_triposr.json`

	Pipeline:
	```
	Prompt > SD 1.5 > TripoSR > GLB
	```

	Specs:
	- Time: ~25-40s
	- VRAM: 4-5GB
	- Best for: Text-based creation

	</td>
	<td width="33%">

	#### 🛳 Advanced - InstantMesh
	`advanced/AIEXX_prompt_to_3d_instantmesh.json`

	Pipeline:
	```
	Prompt > SD > Zero123++ > InstantMesh > GLB
	```

	Specs:
	- Time: ~45-90s
	- VRAM: 5-6GB
	- Best for: High-quality output

	</td>
	</tr>
	</table>

	---

	## ⚙️ Technology Stack

	### Core AI/ML Technologies

	\| Technology \| Version \| Purpose \|
	\|------------\|---------\|----------\|
	\| Python \| 3.11.9 \| Core Language \|
	\| PyTorch \| 2.7.0+cu128 \| Deep Learning Framework \|
	\| CUDA Toolkit \| 12.8 \| GPU Acceleration \|
	\| Stable Diffusion \| 1.5 \| Image Generation \|
	\| TripoSR \| Latest \| 3D Reconstruction \|
	\| torch_scatter \| 2.1.2 \| Sparse Operations \|
	\| ComfyUI \| Latest \| UI Framework \|
	\| ComfyUI-3D-Pack \| Latest \| 3D Nodes & Tools \|

	---

	## 📊 Performance Benchmarks

	### Processing Times (RTX 5060 8GB)

	\| Workflow \| Input Type \| Speed \| VRAM Usage \|
	\|----------\|-----------\|-------\|------------\|
	\| TripoSR (Image>3D) \| Single Image \| 15-30s \| 3-4GB \|
	\| TripoSR (Prompt>3D) \| Text Prompt \| 25-40s \| 4-5GB \|
	\| InstantMesh \| Text Prompt \| 45-90s \| 5-6GB \|
	\| Zero123 Multi-View \| Single Image \| 30-60s \| 4-5GB \|

	---

	## 💫 Acknowledgments

	This project builds upon these amazing open-source projects:

	- [ComfyUI](https://github.com/comfyanonymous/ComfyUI) - Node-based Stable Diffusion GUI
	- [Stable Diffusion](https://github.com/Stability-AI/stablediffusion) - Text-to-image foundation
	- [TripoSR](https://github.com/VAST-AI-Research/TripoSR) - Fast 3D reconstruction from single images
	- [PyTorch](https://pytorch.org/) - Deep learning framework
	- [PyTorch3D](https://pytorch3d.org/) - 3D deep learning library

	Special thanks to:
	- Stability AI for Stable Diffusion
	- NVIDIA for CUDA toolkit and GPU support
	- Hugging Face for model hosting
	- The entire open-source AI community

	---

	## 🔧 Support & Community

	- Issues: [GitHub Issues](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/issues)
	- Docs: [GitHub Wiki](https://github.com/AIExxplorer/AIEXX_GENAI_IMAGE_TO_3D/wiki)
	- Email: [aiexxplorer@artificialuniverse.tech](mailto:aiexxplorer@artificialuniverse.tech)

	---

	## 💫 License

	This project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.

	---

	<div align="center">

	### 🚀 Ready to Transform Ideas into 3D Reality?

	```batch
	6-START_AIEXX.bat
	```

	[⬆ Back to Top](#aiexx-genai-image-to-3d)

	---

	Built with ❤️ by [AIEXX](https://github.com/AIExxplorer)

	Optimized for NVIDIA RTX 5060 \| Powered by AI

	![Footer](https://img.shields.io/badge/Made%20with-Python%20%7C%20PyTorch%20%7C%20CUDA-blue?style=for-the-badge)

	</div>