{"id":49973432,"url":"https://github.com/humansensinglab/fabric-diffusion","last_synced_at":"2026-05-18T09:43:41.022Z","repository":{"id":270661964,"uuid":"838451621","full_name":"humansensinglab/fabric-diffusion","owner":"humansensinglab","description":"[SIGGRAPH Asia 2024] FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Images","archived":false,"fork":false,"pushed_at":"2025-03-04T20:49:34.000Z","size":12559,"stargazers_count":55,"open_issues_count":0,"forks_count":0,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-03-04T21:33:19.129Z","etag":null,"topics":["3d-garment","diffusion-models","pbr-textures"],"latest_commit_sha":null,"homepage":"https://humansensinglab.github.io/fabric-diffusion/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/humansensinglab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-08-05T17:04:22.000Z","updated_at":"2025-03-03T08:21:55.000Z","dependencies_parsed_at":"2025-03-04T21:27:40.539Z","dependency_job_id":"03209993-c9a0-4904-bb67-1381be219bc1","html_url":"https://github.com/humansensinglab/fabric-diffusion","commit_stats":null,"previous_names":["humansensinglab/fabric-diffusion"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/humansensinglab/fabric-diffusion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansensinglab%2Ffabric-diffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansensinglab%2Ffabric-diffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansensinglab%2Ffabric-diffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansensinglab%2Ffabric-diffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/humansensinglab","download_url":"https://codeload.github.com/humansensinglab/fabric-diffusion/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/humansensinglab%2Ffabric-diffusion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33173463,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-18T09:27:30.708Z","status":"ssl_error","status_checked_at":"2026-05-18T09:27:28.300Z","response_time":71,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["3d-garment","diffusion-models","pbr-textures"],"created_at":"2026-05-18T09:43:39.449Z","updated_at":"2026-05-18T09:43:41.017Z","avatar_url":"https://github.com/humansensinglab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FabricDiffusion\n\n[![paper](https://img.shields.io/badge/paper-SIGGRAPHAsia-cyan)](https://dl.acm.org/doi/10.1145/3680528.3687637)\n[![arXiv](https://img.shields.io/badge/arxiv-2410.01801-red)](https://arxiv.org/abs/2410.01801)\n[![webpage](https://img.shields.io/badge/webpage-green)](https://humansensinglab.github.io/fabric-diffusion/)\n[![poster](https://img.shields.io/badge/video-orange)](https://youtu.be/xYiyjwldtWc)\n\n\n## Overview\n\n\u003cp align=\"center\"\u003e\n    \u003cimg src=\"docs/teaser.jpg\" width=\"600px\"/\u003e\n\u003c/p\u003e\n\n\u003e **FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Images**\u003cbr\u003e\n\u003e [Cheng Zhang*](https://czhang0528.github.io/), \n[Yuanhao Wang*](https://harrywang355.github.io/), \n[Francisco Vicente Carrasco](https://www.linkedin.com/in/francisco-vicente-carrasco-32a508144/), \n[Chenglei Wu](https://sites.google.com/view/chengleiwu/),\n[Jinlong Yang](https://is.mpg.de/~jyang), \n[Thabo Beeler](https://thabobeeler.com/), \n[Fernando De la Torre](https://www.cs.cmu.edu/~ftorre/) \n(* indicates equal contribution)\u003cbr\u003e\n\u003e **SIGGRAPH Asia 2024**\n\n\u003c!-- This repo contains the code for training ITI-GEN and generating images that uniformly span across \nthe categories of selected attributes. The main idea behind our approach is leveraging reference images to better represent diverse attributes. \nKey features of our method are:\n- Only need datasets that capture the marginal distribution of individual attributes, bypassing the need for datasets that represent joint distributions of multiple attributes.\n- The learned token embeddings are generalizable across different generative models. --\u003e\n\n\n\n## Updates\n\n\n**[Jan 2 2025]** Inference code released. \n\n**[Oct 2 2024]** Paper released to [Arxiv](https://arxiv.org/pdf/2410.01801).\n\n\n\u003c!-- ## Outline\n- [Installation](#installation)\n- [Data Preparation](#data-preparation)\n- [Training ITI-GEN](#training-iti-gen)\n- [Prompt Prepending](#optional-prompt-prepending)\n- [Generation](#generation)\n  - [Stable Diffusion installation](#stable-diffusion-installation)\n  - [Image generation](#image-generation)\n- [Evaluation](#evaluation)\n- [Acknowledgements](#acknowledgements)\n- [Citation](#citation)\n- [License](#license) --\u003e\n\n\n\n\n## Installation\nRunning the codebase only requires installing a recent version of [PyTorch](https://pytorch.org/get-started/locally/), [Diffusers](https://pypi.org/project/diffusers/) and [Transformers](https://pypi.org/project/transformers/):\n\n```angular2html\ngit clone https://github.com/humansensinglab/fabric-diffusion.git\ncd fabric-diffusion\nconda env create --file=environment.yml\nconda activate fabric-diff\n```\n\n## Usage\n\n**1. Texture Normalization**\n\nRun the following command to normalize texture patches cropped from in-the-wild images:\n\n\u003c!-- \u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/multi_category.png\" style=\"margin-right: 10px;\"  width=\"370px\"\u003e\n  \u003cimg src=\"docs/multi_category_man.png\" width=\"370px\"\u003e\n\u003c/p\u003e --\u003e\n\n```shell\npython inference_texture.py \\\n    --texture_checkpoint='Yuanhao-Harry-Wang/fabric-diffusion-texture' \\\n    --src_dir='data/texture_examples' \\\n    --save_dir='outputs/texture' \\\n    --n_samples=3\n```\n- `--texture_checkpoint`: path to the pre-trained texture model checkpoint.\n- `--src_dir`: path to the directory containing input images.\n- `--save_dir`: path to the output directory.\n- `--n_samples`: number of samples per input.\n\n**2. Print Normalization**\n\nSimilarly, run the following command to normalize print patches cropped from in-the-wild images:\n\n\u003c!-- \u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/multi_category.png\" style=\"margin-right: 10px;\"  width=\"370px\"\u003e\n  \u003cimg src=\"docs/multi_category_man.png\" width=\"370px\"\u003e\n\u003c/p\u003e --\u003e\n\n```shell\npython inference_print.py \\\n    --print_checkpoint='Yuanhao-Harry-Wang/fabric-diffusion-print' \\\n    --src_dir='data/print_examples' \\\n    --save_dir='outputs/print' \\\n    --n_samples=3\n```\n\nThe model checkpoints are hosted on Huggingface here ([texture](https://huggingface.co/Yuanhao-Harry-Wang/fabric-diffusion-texture/tree/main), [print](https://huggingface.co/Yuanhao-Harry-Wang/fabric-diffusion-logo)).\n\nWe are actively adding more features to this repo. Please stay tuned!\n\n\n## Acknowledgements\n- Models\n  - [Stable Diffusion](https://github.com/CompVis/stable-diffusion)\n  - [InstructPix2Pix](https://github.com/timothybrooks/instruct-pix2pix)\n  - [Matfusion](https://github.com/samsartor/matfusion)\n  \n## Citation\nIf you find this repo useful, please cite:\n```\n@inproceedings{zhang2024fabricdiffusion,\n    title     = {{FabricDiffusion}: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Images},\n    author    = {Zhang, Cheng and Wang, Yuanhao and Vicente Carrasco, Francisco and Wu, Chenglei and \n                 Yang, Jinlong and Beeler, Thabo and De la Torre, Fernando},\n    booktitle = {ACM SIGGRAPH Asia},\n    year      = {2024},\n}\n```\n\n## License\nWe use the X11 License. This license is identical to the MIT License, \nbut with an extra sentence that prohibits using the copyright holders' names (Carnegie Mellon University and Google in our case) for \nadvertising or promotional purposes without written permission.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhumansensinglab%2Ffabric-diffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhumansensinglab%2Ffabric-diffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhumansensinglab%2Ffabric-diffusion/lists"}