Update README.md

README.md

@@ -1,3 +1,12 @@
+---
+
+license: mit
+pipeline_tag: image-to-3d
+library_name: diffusers
+tags: ["image-to-3d", "text-to-3d", "3d-generation", "3d-gaussian-splatting", "gaussian-splatting", "multi-view-diffusion", "diffusers", "safetensors", "research"]
+
+---
+
 <div align="center">
 
 # 🐙 WasabiOctopus / LGM
@@ -12,7 +21,7 @@
   <img src="https://img.shields.io/badge/License-MIT-green">
 </p>
 
-**A Diffusers-ready LGM pipeline for fast 3D content creation from text or a single image.**
+**A clean Diffusers-ready LGM release for fast 3D content creation from text or a single image.**
 
 </div>
 
@@ -20,17 +29,17 @@
 
 ## ✨ Highlights
 
-* 🚀 **Fast 3D asset generation** powered by the LGM pipeline.
-* 🧊 **3D Gaussian Splatting representation** for efficient high-resolution 3D content.
-* 🖼️ **Text-to-3D and image-to-3D workflows** through multi-view diffusion.
-* 🧩 **Diffusers-compatible model structure** with `LGMFullPipeline`.
-* 🔬 Useful for **3D generation research, creative prototyping, course projects, and rapid experimentation**.
+* 🚀 Fast 3D asset generation powered by the LGM pipeline.
+* 🧊 3D Gaussian Splatting representation for efficient 3D content creation.
+* 🖼️ Supports text-to-3D and image-to-3D workflows.
+* 🧩 Diffusers-compatible model structure.
+* 🔬 Useful for 3D generation research, creative prototyping, and rapid experimentation.
 
 ---
 
 ## 🖼️ Gallery
 
-> Upload your own generated examples to an `assets/` folder and replace the placeholders below.
+Generated examples will be added soon.
 
 | Prompt / Input                                        | Generated 3D Asset |
 | ----------------------------------------------------- | ------------------ |
@@ -42,9 +51,9 @@
 
 ## 🧠 What is LGM?
 
-**LGM**, short for **Large Multi-View Gaussian Model**, is a 3D generation framework designed for high-resolution 3D content creation.
+**LGM**, short for **Large Multi-View Gaussian Model**, is a 3D generation framework for high-resolution 3D content creation.
 
-Instead of directly generating a mesh from scratch, the pipeline first produces multi-view visual information and then reconstructs a 3D Gaussian representation. This makes it suitable for fast, feed-forward 3D asset generation from either a text prompt or a single input image.
+Instead of directly generating a mesh from scratch, the pipeline first produces multi-view visual information and then reconstructs a 3D Gaussian representation. This makes it suitable for fast feed-forward 3D asset generation from either a text prompt or a single input image.
 
 This repository provides a convenient Hugging Face / Diffusers-style release of the full LGM pipeline.
 
@@ -52,19 +61,12 @@ This repository provides a convenient Hugging Face / Diffusers-style release of
 
 ## 🏗️ Pipeline Overview
 
-```text
 Text prompt or single image
-        ↓
-Multi-view diffusion generation
-        ↓
-Multi-view Gaussian features
-        ↓
-LGM reconstruction module
-        ↓
-3D Gaussian asset
-        ↓
-PLY export / downstream rendering
-```
+→ Multi-view diffusion generation
+→ Multi-view Gaussian features
+→ LGM reconstruction module
+→ 3D Gaussian asset
+→ PLY export / downstream rendering
 
 ---
 
@@ -72,17 +74,15 @@ PLY export / downstream rendering
 
 ### 1. Install dependencies
 
-```bash
+```
 pip install -U diffusers transformers accelerate safetensors
 pip install torch torchvision torchaudio
 pip install xformers trimesh kiui plyfile
 ```
 
-For the full environment, check the repository `requirements.txt`.
-
 ### 2. Load the pipeline
 
-```python
+```
 import torch
 from diffusers import DiffusionPipeline
 
@@ -99,7 +99,7 @@ pipe = pipe.to("cuda")
 
 ### 3. Text-to-3D generation
 
-```python
+```
 prompt = "a cute robot, smooth toy material, studio lighting, clean geometry"
 
 gaussians = pipe(
@@ -113,7 +113,7 @@ pipe.save_ply(gaussians, "robot.ply")
 
 ### 4. Image-to-3D generation
 
-```python
+```
 import numpy as np
 from PIL import Image
 
@@ -134,7 +134,7 @@ pipe.save_ply(gaussians, "asset_from_image.ply")
 
 ## 📦 Repository Contents
 
-```text
+```
 WasabiOctopus/LGM
 ├── README.md
 ├── model_index.json
@@ -156,8 +156,8 @@ WasabiOctopus/LGM
 
 This model release is useful for:
 
-* Fast **single-image-to-3D** prototyping
-* **Text-to-3D** creative asset generation
+* Fast single-image-to-3D prototyping
+* Text-to-3D creative asset generation
 * 3D generation course projects
 * Research demos around 3D Gaussian Splatting
 * Benchmarking recent 3D asset generation pipelines
@@ -183,18 +183,14 @@ For professional 3D asset production, additional post-processing may be needed,
 
 Good prompts usually describe:
 
-```text
-object category + style + material + lighting + geometry constraint
-```
+**object category + style + material + lighting + geometry constraint**
 
 Examples:
 
-```text
-a cute robot, rounded toy design, smooth plastic material, studio lighting
-a medieval treasure chest, golden metal details, wooden texture, clean geometry
-a sci-fi helmet, hard-surface design, matte black material, sharp edges
-a tiny house, stylized low-poly, warm colors, isometric game asset
-```
+* `a cute robot, rounded toy design, smooth plastic material, studio lighting`
+* `a medieval treasure chest, golden metal details, wooden texture, clean geometry`
+* `a sci-fi helmet, hard-surface design, matte black material, sharp edges`
+* `a tiny house, stylized low-poly, warm colors, isometric game asset`
 
 For image-to-3D, use images with:
 
@@ -217,7 +213,9 @@ For image-to-3D, use images with:
 
 ## 🙏 Acknowledgements
 
-This repository is based on the LGM ecosystem and the upstream Hugging Face full pipeline release. Full credit for the original LGM method goes to the authors of:
+This repository is based on the LGM ecosystem and the upstream Hugging Face full pipeline release.
+
+Full credit for the original LGM method goes to the authors of:
 
 **LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation**
 
@@ -229,7 +227,7 @@ This release is intended as a convenient Hugging Face / Diffusers-compatible res
 
 If you use this model or the original LGM method, please cite:
 
-```bibtex
+```
 @article{tang2024lgm,
   title={LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation},
   author={Tang, Jiaxiang and Chen, Zhaoxi and Chen, Xiaokang and Wang, Tengfei and Zeng, Gang and Liu, Ziwei},