Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[CVPR2024 (Highlight)] RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D. Live Demo：https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC
| Date | Stars |
|---|---|
| 2026-07-31 | 478 |
| 2026-08-01 | 478 |
| 2026-08-06 | 478 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center">
<br>
<img src="https://modelscope.oss-cn-beijing.aliyuncs.com/modelscope.gif" width="400"/>
<br>
<h1>RichDreamer</h1>
<p>
RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D.
[Lingteng Qiu\*](https://lingtengqiu.github.io/),
[Guanying Chen\*](https://guanyingc.github.io/),
[Xiaodong Gu\*](https://scholar.google.com.hk/citations?user=aJPO514AAAAJ&hl=zh-CN&oi=ao),
Qi Zuo,
[Mutian Xu](https://mutianxu.github.io/),
Yushuang Wu,
[Weihao Yuan](https://weihao-yuan.com/),
[Zilong Dong](https://scholar.google.com/citations?user=GHOQKCwAAAAJ&hl=zh-CN&oi=ao),
[Liefeng Bo](https://research.cs.washington.edu/istc/lfb/),
[Xiaoguang Han](https://gaplab.cuhk.edu.cn/)
如果您熟悉中文，可以阅读[中文版本的README](./README_ZH.md)。
Our method is based on Normal-Depth diffusion Model, for more details please refer to [normal-depth-diffusion](https://github.com/modelscope/normal-depth-diffusion).
## [Project page](https://aigc3d.github.io/richdreamer) | [Paper](https://arxiv.org/abs/2311.16918) | [YouTube](https://youtu.be/6gQ1VWiKoc0) | [ND-Diffusion Model](https://github.com/modelscope/normal-depth-diffusion) | [3D Rendering Dataset](https://aigc3d.github.io/gobjaverse)
<img src=".\figs\richdreamer.gif" alt="richdreamer" style="zoom:200%;" />
## TODO :triangular_flag_on_post:
- [x] Text to ND Diffusion Model
- [x] Multiview-ND and Multiview-Albedo Diffusion Models
- [x] Release code
- [x] Provide the generation trial on [ModelScope's 3D Object Generation](https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC/summary)
- [x] Docker image
## News
- RichDreamer is got accepted by CVPR2024. (**Highlight**) (04.04, 2024 UTC)
- [ModelScope's 3D Object Generation](https://modelscope.cn/studios/Damo_XR_Lab/3D_AIGC/summary) is online. Have a try :fire::fire::fire: (12.22, 2023 UTC)
- Release RichDreamer :fire::fire::fire: (12.11, 2023 UTC)
## Architecture
# Install
- System requirement: Ubuntu20.04
- Tested GPUs: RTX4090, A100
Install requirements using following scripts.
```bash
git clone https://github.com/modelscope/RichDreamer.git --recursive
conda create -n rd
conda activate rd
# install dependence of threestudio
pip install -r requirements_3d.txt
```
we also provide a dockerfile to build docker image or use our built [docker image](registry.cn-hangzhou.aliyuncs.com/ailab-public/aigc3d).
```bash
sudo docker build -t mv3dengine_22.04:cu118 -f docker/Dockerfile .
# or use our built docker image
sudo docker pull registry.cn-hangzhou.aliyuncs.com/ailab-public/aigc3d
```
Download pretrained weights.
1. MultiView Normal-Depth Diffusion Model (ND-MV)
2. MultiView Depth-conditioned Albedo Diffusion Model (Alebdo-MV)
**Or** your can download weights using the following scripts.
```bash
python tools/download_nd_models.py
# copy 256_tets file for dmtet.
cp ./pretrained_models/Damo_XR_Lab/Normal-Depth-Diffusion-Model/256_tets.npz ./load/tets/
# link your huggingface models to ./pretrained_models/huggingface
cd pretrained_models && ln -s ~/.cache/huggingface ./
```
if you cannot visit huggingface to download SD 1.5, SD 2.1 and CLIPs, you can download SD and CLIP models from [aliyun](https://virutalbuy-public.oss-cn-hangzhou.aliyuncs.com/share/RichDreamer/models_sd_clip.tar.gz) and then put `$download_sd_clip` file to `pretrained_models/huggingface/hub/`.
```bash
mkdir -p pretrained_models/huggingface/hub/
cd pretrained_models/huggingface/hub/
mv /path/to/${download_sd_clip} ./
tar -xvf ${download_sd_clip} ./
```
## Generation
Make sure you have the following models.
```bash
RichDreamer
|-- pretrained_models
|-- Damo_XR_Lab
|-- Normal-Depth-Diffusion-Model
|-- nd_mv_ema.ckpt
|-- albedo_mv_ema.ckpt
|-- huggingface
|-- hub
|-- models--runwayml--stable-diffusion-v1-5
|-- models--openai--clip-vit-large-patch14
|-- models--stabilityai--stable-diffusion-2-1-bExcerpt of 8,110 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c87434666a500e59, desc:diffusion model