{"id":13723909,"url":"https://github.com/3DTopia/3DTopia","last_synced_at":"2025-05-07T17:32:06.835Z","repository":{"id":218558657,"uuid":"745337912","full_name":"3DTopia/3DTopia","owner":"3DTopia","description":"Text-to-3D Generation within 5 Minutes","archived":false,"fork":false,"pushed_at":"2024-03-10T05:08:10.000Z","size":21389,"stargazers_count":588,"open_issues_count":10,"forks_count":40,"subscribers_count":12,"default_branch":"main","last_synced_at":"2024-08-04T01:23:13.637Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/3DTopia.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-01-19T05:44:41.000Z","updated_at":"2024-08-03T11:48:47.000Z","dependencies_parsed_at":"2024-02-01T10:25:47.330Z","dependency_job_id":"b84f1b8f-d7de-4a3d-b6ad-5e380561a1ef","html_url":"https://github.com/3DTopia/3DTopia","commit_stats":null,"previous_names":["3dtopia/3dtopia"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/3DTopia%2F3DTopia","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/3DTopia%2F3DTopia/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/3DTopia%2F3DTopia/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/3DTopia%2F3DTopia/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/3DTopia","download_url":"https://codeload.github.com/3DTopia/3DTopia/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":224628213,"owners_count":17343292,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-03T01:01:47.057Z","updated_at":"2024-11-14T13:31:17.752Z","avatar_url":"https://github.com/3DTopia.png","language":"Python","funding_links":[],"categories":["\u003cspan id=\"model\"\u003e3D Model\u003c/span\u003e","Python","AI \u0026 Machine Learning for CG"],"sub_categories":["\u003cspan id=\"tool\"\u003eLLM (LLM \u0026 Tool)\u003c/span\u003e","3D Generation"],"readme":"\u003cp align=\"center\"\u003e\n    \u003cpicture\u003e\n    \u003cimg alt=\"logo\" src=\"assets/3dtopia.jpeg\" width=\"20%\"\u003e\n    \u003c/picture\u003e\n\u003c/p\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ch1\u003e3DTopia\u003c/h1\u003e\n  \u003cp\u003e\n      A two-stage text-to-3D generation model. The first stage uses diffusion model to quickly generate candidates. The second stage refines the assets chosen from the first stage.\n  \u003c/p\u003e\n  \u003cimg src=\"https://visitor-badge.laobi.icu/badge?page_id=3DTopia.3DTopia\" /\u003e\n\n  \u003cp\u003e\n       \n  \u003c/p\u003e\n\nhttps://github.com/3DTopia/3DTopia/assets/23376858/c9716cf0-6e61-4983-82b2-2e8f579bd46c\n    \n\u003c/div\u003e\n\n## News\n\n[2024/03/10] Our captions for Objaverse is released [here](https://github.com/3DTopia/3DTopia/releases).\n\n[2024/03/04] Our technical report is released [here](https://arxiv.org/pdf/2403.02234.pdf).\n\n[2024/01/18] We release a text-to-3D model 3DTopia!\n\n## Citation\n```\n@article{hong20243dtopia,\n  title={3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors},\n  author={Hong, Fangzhou and Tang, Jiaxiang and Cao, Ziang and Shi, Min and Wu, Tong and Chen, Zhaoxi and Wang, Tengfei and Pan, Liang and Lin, Dahua and Liu, Ziwei},\n  journal={arXiv preprint arXiv:2403.02234},\n  year={2024}\n}\n```\n\n## 1. Quick Start\n\n### 1.1 Install Environment for this Repository\nWe recommend using Anaconda to manage the environment.\n```bash\nconda env create -f environment.yml\n```\n\n### 1.2 Install Second Stage Refiner\nPlease refer to [threefiner](https://github.com/3DTopia/threefiner) to install our second stage mesh refiner. We have tested installing both environments together with Pytorch 1.12.0 and CUDA 11.3.\n\n### 1.3 Download Checkpoints \\[Optional\\]\nWe have implemented automatic checkpoint download for both `gradio_demo.py` and `sample_stage1.py`. If you prefer to download manually, you may download checkpoint `3dtopia_diffusion_state_dict.ckpt` or `model.safetensors` from [huggingface](https://huggingface.co/hongfz16/3DTopia).\n\n### Q\u0026A\n- If you encounter this error in the second stage `ImportError: /lib64/libc.so.6: version 'GLIBC_2.25' not found`, try to install a lower version of pymeshlab by `pip install pymeshlab==0.2`.\n\n## 2. Inference\n\n### 2.1 First Stage\nRun the following command to sample `a robot` as the first stage. Results will be located under the folder `results`.\n```bash\npython -u sample_stage1.py --text \"a robot\" --samples 1 --sampler ddim --steps 200 --cfg_scale 7.5 --seed 0\n```\n\nArguments:\n- `--ckpt` specifies checkpoint file path;\n- `--test_folder` controls which subfolder to put all the results;\n- `--seed` will fix random seeds; `--sampler` can be set to `ddim` for DDIM sampling (By default, we use 1000 steps DDPM sampling);\n- `--steps` controls sampling steps only for DDIM;\n- `--samples` controls number of samples;\n- `--text` is the input text;\n- `--no_video` and `--no_mcubes` suppress rendering multi-view videos and marching cubes, which are by-default enabled;\n- `--mcubes_res` controls the resolution of the 3D volumn sampled for marching cubes; One can lower this resolution to save graphics memory;\n- `--render_res` controls the resolution of the rendered video;\n\n### 2.2 Second Stage\nThere are two steps as the second stage refinement. Here is a simple example. Please refer to [threefiner](https://github.com/3DTopia/threefiner) for more detailed usage.\n```bash\n# step 1\nthreefiner sd --mesh results/default/stage1/a_robot_0_0.ply --prompt \"a robot\" --text_dir --front_dir='-y' --outdir results/default/stage2/ --save a_robot_0_0_sd.glb\n# step 2\nthreefiner if2 --mesh results/default/stage2/a_robot_0_0_sd.glb --prompt \"a robot\" --outdir results/default/stage2/ --save a_robot_0_0_if2.glb\n```\nThe resulting mesh can be found at `results/default/stage2/a_robot_0_0_if2.glb`\n\n## 3. Acknowledgement\nWe thank the community for building and open-sourcing the foundation of this work. Specifically, we want to thank [EG3D](https://github.com/NVlabs/eg3d), [Stable Diffusion](https://github.com/CompVis/stable-diffusion) for their codes. We also want to thank [Objaverse](https://objaverse.allenai.org) for the wonderful dataset.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F3DTopia%2F3DTopia","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F3DTopia%2F3DTopia","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F3DTopia%2F3DTopia/lists"}