Update README.md

README.md

@@ -1,10 +1,10 @@
 ---
-
 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"]
-
+base_model: "dylanebert/LGM-full"
+tags: ["image-to-3d", "text-to-3d", "3d-generation", "3d-gaussian-splatting", "gaussian-splatting", "multi-view-diffusion", "lgm", "diffusers", "safetensors", "objaverse", "research", "computer-graphics"]
+arxiv: "2402.05054"
 ---
 
 <div align="center">
@@ -21,68 +21,67 @@ tags: ["image-to-3d", "text-to-3d", "3d-generation", "3d-gaussian-splatting", "g
   <img src="https://img.shields.io/badge/License-MIT-green">
 </p>
 
-**A clean Diffusers-ready LGM release for fast 3D content creation from text or a single image.**
+**A Diffusers-ready LGM pipeline for fast 3D content creation from text or a single image.**
 
 </div>
 
----
-
 ## ✨ Highlights
 
-* 🚀 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.
-
----
+- 🚀 **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**.
 
 ## 🖼️ Gallery
 
-Generated examples will be added soon.
-
-| Prompt / Input                                        | Generated 3D Asset |
-| ----------------------------------------------------- | ------------------ |
-| `a cute robot, smooth toy material, studio lighting`  | Coming soon        |
-| `a fantasy treasure chest with golden details`        | Coming soon        |
-| `a stylized sci-fi helmet, clean hard-surface design` | Coming soon        |
+> Upload your own generated examples to an `assets/` folder and replace the placeholders below.
 
----
+| Prompt / Input | Generated 3D Asset |
+|---|---|
+| `a cute robot, smooth toy material, studio lighting` | Coming soon |
+| `a fantasy treasure chest with golden details` | Coming soon |
+| `a stylized sci-fi helmet, clean hard-surface design` | Coming soon |
 
 ## 🧠 What is LGM?
 
-**LGM**, short for **Large Multi-View Gaussian Model**, is a 3D generation framework for high-resolution 3D content creation.
+**LGM**, short for **Large Multi-View Gaussian Model**, is a 3D generation framework designed 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.
 
----
-
 ## 🏗️ 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
+```
 
 ## 🚀 Quick Start
 
 ### 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 +98,7 @@ 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 +112,7 @@ pipe.save_ply(gaussians, "robot.ply")
 
 ### 4. Image-to-3D generation
 
-```
+```python
 import numpy as np
 from PIL import Image
 
@@ -130,11 +129,9 @@ gaussians = pipe(
 pipe.save_ply(gaussians, "asset_from_image.ply")
 ```
 
----
-
 ## 📦 Repository Contents
 
-```
+```text
 WasabiOctopus/LGM
 ├── README.md
 ├── model_index.json
@@ -150,84 +147,74 @@ WasabiOctopus/LGM
 └─�� lgm/
 ```
 
----
-
 ## 💡 Recommended Use Cases
 
 This model release is useful for:
 
-* 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
-* Building lightweight demos for Blender, Unity, or web-based 3D viewers
-
----
+- 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
+- Building lightweight demos for Blender, Unity, or web-based 3D viewers
 
 ## ⚠️ Limitations
 
 This model is a research-oriented 3D generation pipeline. It may produce imperfect geometry or artifacts in the following cases:
 
-* Thin structures, transparent objects, wires, fur, or complex topology
-* Highly reflective or texture-heavy objects
-* Ambiguous single-view inputs where the back side is not visible
-* Prompt-only generation requiring precise physical dimensions
-* Production workflows requiring clean quad meshes, rigging, or CAD-level topology
+- Thin structures, transparent objects, wires, fur, or complex topology
+- Highly reflective or texture-heavy objects
+- Ambiguous single-view inputs where the back side is not visible
+- Prompt-only generation requiring precise physical dimensions
+- Production workflows requiring clean quad meshes, rigging, or CAD-level topology
 
 For professional 3D asset production, additional post-processing may be needed, such as mesh extraction, topology cleanup, UV unwrapping, material editing, or manual refinement.
 
----
-
 ## 🧪 Tips for Better Results
 
 Good prompts usually describe:
 
-**object category + style + material + lighting + geometry constraint**
+```text
+object category + style + material + lighting + geometry constraint
+```
 
 Examples:
 
-* `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`
+```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
+```
 
 For image-to-3D, use images with:
 
-* A single centered object
-* Clean background
-* Clear object silhouette
-* Minimal occlusion
-* Good lighting
-
----
+- A single centered object
+- Clean background
+- Clear object silhouette
+- Minimal occlusion
+- Good lighting
 
 ## 🔗 Related Links
 
-* Original paper: https://arxiv.org/abs/2402.05054
-* Original project page: https://me.kiui.moe/lgm/
-* Original GitHub repository: https://github.com/3DTopia/LGM
-* Upstream Hugging Face model: https://huggingface.co/dylanebert/LGM-full
-
----
+- Original paper: https://arxiv.org/abs/2402.05054
+- Original project page: https://me.kiui.moe/lgm/
+- Original GitHub repository: https://github.com/3DTopia/LGM
+- Upstream Hugging Face model: https://huggingface.co/dylanebert/LGM-full
 
 ## 🙏 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**
 
 This release is intended as a convenient Hugging Face / Diffusers-compatible resource for research, education, and rapid experimentation.
 
----
-
 ## 📚 Citation
 
 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},
@@ -236,12 +223,10 @@ If you use this model or the original LGM method, please cite:
 }
 ```
 
----
-
 <div align="center">
 
 ### 🐙 Built for fast 3D generation experiments.
 
 **From prompt or image to 3D Gaussian assets — clean, simple, and research-friendly.**
 
-</div>
+</div>