{"id":13771905,"url":"https://github.com/bcmi/Awesome-Generative-Image-Composition","last_synced_at":"2025-05-11T04:31:00.822Z","repository":{"id":183332532,"uuid":"669957067","full_name":"bcmi/Awesome-Generative-Image-Composition","owner":"bcmi","description":"A curated list of papers, code, and resources pertaining to generative image composition or object insertion. ","archived":false,"fork":false,"pushed_at":"2025-05-02T05:27:18.000Z","size":3054,"stargazers_count":117,"open_issues_count":0,"forks_count":7,"subscribers_count":8,"default_branch":"main","last_synced_at":"2025-05-02T06:27:22.555Z","etag":null,"topics":["diffusion-model","image-composition","object-insertion"],"latest_commit_sha":null,"homepage":"","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/bcmi.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,"zenodo":null}},"created_at":"2023-07-24T01:10:09.000Z","updated_at":"2025-05-02T05:27:21.000Z","dependencies_parsed_at":null,"dependency_job_id":"a0e1d93f-60a1-471b-9414-49ba2c87ef1c","html_url":"https://github.com/bcmi/Awesome-Generative-Image-Composition","commit_stats":null,"previous_names":["bcmi/awesome-generative-image-composition"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcmi%2FAwesome-Generative-Image-Composition","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcmi%2FAwesome-Generative-Image-Composition/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcmi%2FAwesome-Generative-Image-Composition/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bcmi%2FAwesome-Generative-Image-Composition/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bcmi","download_url":"https://codeload.github.com/bcmi/Awesome-Generative-Image-Composition/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253518941,"owners_count":21921074,"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":["diffusion-model","image-composition","object-insertion"],"created_at":"2024-08-03T17:00:57.429Z","updated_at":"2025-05-11T04:31:00.789Z","avatar_url":"https://github.com/bcmi.png","language":"Python","funding_links":[],"categories":["Papers","Datasets","Other Lists","Attribution"],"sub_categories":["TeX Lists","AI-Assisted CG Software"],"readme":"\n# Awesome Generative Image Composition [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)\n\nA curated list of resources including papers, datasets, and relevant links pertaining to generative image composition (object insertion). **Generative image composition aims to generate plausible composite images based on a background image (optional bounding box) and a (*resp.*, a few) foreground image (*resp.*, images) of a specific object.** For more complete resources on general image composition ([object insertion](https://github.com/bcmi/Awesome-Object-Insertion)), please refer to [Awesome-Image-Composition](https://github.com/bcmi/Awesome-Object-Insertion).\n\n\u003cp align='center'\u003e  \n  \u003cimg src='./figures/task.jpg'  width=90% /\u003e\n\u003c/p\u003e\n\n## Contributing\n\nContributions are welcome.  If you wish to contribute, feel free to send a pull request. If you have suggestions for new sections to be included, please raise an issue and discuss before sending a pull request.\n\n## Table of Contents\n+ [Survey](#Survey)\n+ [Online Demo](#Online-demo)\n+ [Evaluation Metrics](#Evaluation-metrics)\n+ [Datasets](#Datasets)\n+ [Leaderboard](#Leaderboard)\n+ [Papers](#Papers)\n+ [Related Topics](#Related-topics)\n+ [Other Resources](#Other-resources)\n\n## Survey\n\nA brief review on generative image composition is included in the following survey on image composition:\n\nLi Niu, Wenyan Cong, Liu Liu, Yan Hong, Bo Zhang, Jing Liang, Liqing Zhang: \"*Making Images Real Again: A Comprehensive Survey on Deep Image Composition.*\" arXiv preprint arXiv:2106.14490 (2021). [[arXiv]](https://arxiv.org/pdf/2106.14490.pdf)  [[slides]](https://www.ustcnewly.com/download/Image_composition_tutorial.pdf)\n\n\n## Online Demo\n\nTry this [online demo](https://bcmi.sjtu.edu.cn/home/niuli/demo_image_composition/) for generative image composition and have fun! ![hot](https://bcmi.sjtu.edu.cn/~niuli/images/fire.png)\n\n\n## Evaluation Metrics\n\n+ [Composite-Image-Evaluation](https://github.com/bcmi/Composite-Image-Evaluation)\n\n\n## Datasets\n\n+ [COCOEE](https://github.com/Fantasy-Studio/Paint-by-Example?tab=readme-ov-file#test-benchmark) (within-domain, single-ref): 500 background images from MSCOCO validation set.  Each background image has a bounding box and a foreground image from MSCOCO training set.\n+ [TF-ICON test benchmark](https://github.com/Shilin-LU/TF-ICON?tab=readme-ov-file#tf-icon-test-benchmark) (cross-domain, single-ref): 332 samples. Each sample consists of a background image, a foreground image, a\nuser mask, and a text prompt.\n+ [DreamEditBench](https://huggingface.co/datasets/tianleliphoebe/DreamEditBench) (within-domain, multi-ref): 220 background images and 30 unique foreground objects from 15 categories. \n+ [MureCom](https://github.com/bcmi/DreamCom-Image-Composition?tab=readme-ov-file#our-murecom-dataset) (within-domain, multi-ref): 640 background images and 96 unique foreground objects from 32 categories.\n+ [SAM-FB](https://github.com/KaKituken/affordance-aware-any) (within-domain, single-ref): built upon SA-1B (SAM dataset). 3,160,403 images with 3,439 foreground categories.\n+ [Subjects 200K](https://github.com/Yuanshi9815/Subjects200K) (within-domain, double-ref): 200,000 paired images. Each pair has the same subject yet various scene contexts.\n\n## Leaderboard\n\nThe training set is open. The test set is [COCOEE](https://github.com/Fantasy-Studio/Paint-by-Example?tab=readme-ov-file#test-benchmark) benchmark. Partial results are copied from [ControlCom](https://github.com/bcmi/ControlCom-Image-Composition). Honestly speaking, the following evaluation metrics are not very reliable. For more comprehensive and interpretable evaluation, you can refer to this [summary](https://github.com/bcmi/Composite-Image-Evaluation) of evaluation metrics.\n\n\u003ctable class=\"tg\"\u003e\n  \u003ctr\u003e\n    \u003cth class=\"tg-0pky\" rowspan=\"2\" align=\"center\"\u003eMethod\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" colspan=\"3\" align=\"center\"\u003eForeground\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" colspan=\"2\" align=\"center\"\u003eBackground\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" colspan=\"2\" align=\"center\"\u003eOverall\u003c/th\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003eCLIP\u0026uarr;\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003eDINO\u0026uarr;\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003eFID\u0026darr;\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003eLSSIM\u0026uarr;\u003c/th\u003e    \n    \u003cth class=\"tg-0pky\" align=\"center\"\u003eLPIPS\u0026darr;\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003eFID\u0026darr;\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003eQS\u0026uarr;\u003c/th\u003e\n  \u003c/tr\u003e\n\u003ctr\u003e\n  \u003cth class=\"tg-0pky\" align=\"center\"\u003eInpaint\u0026Paste\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e-\u003c/th\u003e\n  \u003cth class=\"tg-0pky\" align=\"center\"\u003e-\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e8.0\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e-\u003c/th\u003e    \n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e-\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e3.64\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e72.07\u003c/th\u003e\n  \u003c/tr\u003e\n  \u003cth class=\"tg-0pky\" align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2211.13227.pdf\"\u003ePBE\u003c/a\u003e \u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e84.84\u003c/th\u003e\n  \u003cth class=\"tg-0pky\" align=\"center\"\u003e52.52\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e6.24\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e0.823\u003c/th\u003e    \n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e0.116\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e3.18\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e77.80\u003c/th\u003e\n  \u003c/tr\u003e   \n  \u003cth class=\"tg-0pky\" align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2212.00932.pdf\"\u003eObjectStitch\u003c/a\u003e\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e85.97\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e61.12\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e6.86\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e0.825\u003c/th\u003e    \n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e0.116\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e3.35\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e76.86\u003c/th\u003e\n  \u003c/tr\u003e  \n  \n  \u003cth class=\"tg-0pky\" align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2307.09481.pdf\"\u003eAnyDoor\u003c/a\u003e\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e89.7\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e70.16\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e10.5\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e0.870\u003c/th\u003e    \n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e0.109\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e3.60\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e76.18\u003c/th\u003e\n  \u003c/tr\u003e\n  \u003cth class=\"tg-0pky\" align=\"center\"\u003e\u003ca href=\"https://arxiv.org/pdf/2308.10040.pdf\"\u003eControlCom\u003c/a\u003e\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e88.31\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e63.67\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e6.28\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e0.826\u003c/th\u003e    \n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e0.114\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e3.19\u003c/th\u003e\n    \u003cth class=\"tg-0pky\" align=\"center\"\u003e77.84\u003c/th\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n### Evaluating Your Results\n\n1. **Install Dependencies**:\n   - Begin by installing the dependencies listed in [requirements.txt](./requirements.txt).\n   - Additionally, install [Segment Anything](https://github.com/facebookresearch/segment-anything).\n\n2. **Clone Repository and Download Pretrained Models**:\n   - Clone this repository and ensure you have a `checkpoints` folder.\n   - Download the following pretrained models into the `checkpoints` folder:\n     - [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32): Used for CLIP score and FID score calculations.\n     - [ViT-H SAM model](https://github.com/facebookresearch/segment-anything?tab=readme-ov-file#model-checkpoints): Utilized to estimate foreground masks for reference images and generated composites.\n     - [facebook/dino-vits16](https://huggingface.co/facebook/dino-vits16): Employed in DINO score computation.\n     - [coco2017_gmm_k20](https://github.com/Fantasy-Studio/Paint-by-Example#qs-score): Utilized to compute the overall quality score.\n\n   The resulting folder structure should resemble the following:\n   ```shell\n   checkpoints/\n   ├── clip-vit-base-patch32\n   ├── coco2017_gmm_k20\n   ├── dino-vits16\n   └── sam_vit_h_4b8939.pth\n   ```\n\n\u003c!-- 3. **Download Cache File for FID Scores**:\n   - Download the cache file from [Google Drive](https://drive.google.com/file/d/1m5EXLb2fX95uyl2dYtQUudjnFsGhN5dU/view?usp=sharing) used for computing FID scores.\n   - Unzip the cache file to a `cache` folder as follows:\n     ```shell\n     cache/\n     ├── coco2017_test.pth\n     └── cocoee_gtfg.pth\n     ```\n   Alternatively, you can download the test set of [COCO2017](http://images.cocodataset.org/zips/test2017.zip) in advance and unzip it to a `data` folder. --\u003e\n\n3. **Prepare COCOEE Benchmark and Your Results**:\n   - Prepare the [COCOEE benchmark](https://github.com/Fantasy-Studio/Paint-by-Example?tab=readme-ov-file#test-benchmark) alongside your generated composite results. Ensure that your composite images have filenames corresponding to the background images of the COCOEE dataset, as illustrated below:\n      ```shell\n      results/\n      ......\n      ├── 000002228519_GT.png\n      ├── 000002231413_GT.png\n      ├── 900100065455_GT.png\n      └── 900100376112_GT.png\n      ```\n   - Modify the paths accordingly in the `run.sh` file. If you have downloaded the cache file mentioned earlier, please ignore `cocodir`.\n   - Execute the following command:\n     ```shell\n     sh run.sh\n     ```\n   Then, wait for the results of all metrics to be computed.\n\n\n## Papers\n\n### Training-free\n+ Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin: \"*PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering.*\" ACM MM (2024) [[pdf]](https://dl.acm.org/doi/pdf/10.1145/3664647.3680848) [[code]](https://github.com/CodeGoat24/PrimeComposer)\n+ Shilin Lu, Yanzhu Liu, Adams Wai-Kin Kong: \"*TF-ICON: Diffusion-based Training-free Cross-domain Image Composition.*\" ICCV (2023) [[pdf]](https://openaccess.thecvf.com/content/ICCV2023/papers/Lu_TF-ICON_Diffusion-Based_Training-Free_Cross-Domain_Image_Composition_ICCV_2023_paper.pdf) [[code]](https://github.com/Shilin-LU/TF-ICON)\n+ Roy Hachnochi, Mingrui Zhao, Nadav Orzech, Rinon Gal, Ali Mahdavi-Amiri, Daniel Cohen-Or, Amit Haim Bermano: \"*Cross-domain Compositing with Pretrained Diffusion Models.*\" arXiv preprint arXiv:2302.10167 (2023) [[arXiv]](https://arxiv.org/pdf/2302.10167.pdf) [[code]](https://github.com/roy-hachnochi/cross-domain-compositing)\n\n### Training-based\n+ Gemma Canet Tarrés, Zhe Lin, Zhifei Zhang, He Zhang, Andrew Gilbert, John Collomosse, Soo Ye Kim: \"*Multitwine: Multi-Object Compositing with Text and Layout Control.*\" arXiv preprint arXiv:2502.05165 (2025)  [[arXiv]](https://arxiv.org/pdf/2502.05165) \n+ Xi Chen, Lianghua Huang, Yu Liu, Yujun Shen, Deli Zhao, Hengshuang Zhao: \"*AnyDoor: Zero-shot Image Customization with Region-to-region Reference.*\"  T-PAMI (2025) [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=10976616)\n+ Wensong Song, Hong Jiang, Zongxing Yang, Ruijie Quan, Yi Yang: \"*Insert Anything: Image Insertion via In-Context Editing in DiT.*\" arXiv preprint arXiv:2504.15009 (2025) [[arXiv]](https://arxiv.org/pdf/2504.15009) [[code]](https://github.com/song-wensong/insert-anything)\n+ Jiaxuan Chen, Bo Zhang, Qingdong He, Jinlong Peng, Li Niu: \"*MureObjectStitch: Multi-reference Image Composition.*\" arXiv preprint arXiv:2411.07462 (2025) [[arXiv]](https://arxiv.org/pdf/2411.07462) [[code]](https://github.com/bcmi/MureObjectStitch-Image-Composition)\n+ Haoxuan Wang, Jinlong Peng, Qingdong He, Hao Yang, Ying Jin, Jiafu Wu, Xiaobin Hu, Yanjie Pan, Zhenye Gan, Mingmin Chi, Bo Peng, Yabiao Wang: \"*UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer.*\" arXiv preprint arXiv:2503.09277 (2025) [[arXiv]](https://arxiv.org/pdf/2503.09277) [[code]](https://github.com/Xuan-World/UniCombine)\n+ Yongsheng Yu, Ziyun Zeng, Haitian Zheng, Jiebo Luo: \"*OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting.*\" arXiv preprint arXiv:2503.08677 (2025) [[arXiv]](https://arxiv.org/pdf/2503.08677) [[code]](https://github.com/yeates/OmniPaint)\n+ Nataniel Ruiz, Yuanzhen Li, Neal Wadhwa, Yael Pritch, Michael Rubinstein, David E. Jacobs, Shlomi Fruchter: \"*Magic Insert: Style-Aware Drag-and-Drop.*\" arXiv preprint arXiv:2407.02489 (2024) [[arXiv]](https://arxiv.org/pdf/2407.02489)\n+ Jixuan He, Wanhua Li, Ye Liu, Junsik Kim, Donglai Wei, Hanspeter Pfister: \"*Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion.*\" arXiv preprint arXiv:2412.14462 (2024)  [[arXiv]](https://arxiv.org/pdf/2412.14462) [[code]](https://github.com/KaKituken/affordance-aware-any)\n+ Daniel Winter, Asaf Shul, Matan Cohen, Dana Berman, Yael Pritch, Alex Rav-Acha, Yedid Hoshen: \"*ObjectMate: A Recurrence Prior for Object Insertion and Subject-Driven Generation.*\" arXiv preprint arXiv:2412.08645 (2024)  [[arXiv]](https://arxiv.org/pdf/2412.08645)\n+ Zitian Zhang, Frederic Fortier-Chouinard, Mathieu Garon, Anand Bhattad, Jean-Francois Lalonde: \"*ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion.*\" arXiv preprint arXiv:2410.08168 (2024) [[arXiv]](https://arxiv.org/pdf/2410.08168) [[code]](https://github.com/lvsn/ZeroComp)\n+ Zhekai Chen, Wen Wang, Zhen Yang, Zeqing Yuan, Hao Chen, Chunhua Shen: \"*FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior.*\" ECCV (2024) [[pdf]](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/02529.pdf) [[code]](https://github.com/aim-uofa/FreeCompose)\n+ Daniel Winter, Matan Cohen, Shlomi Fruchter, Yael Pritch, Alex Rav-Acha, Yedid Hoshen: \"*ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion.*\"  ECCV (2024) [[pdf]](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/09857.pdf)\n+ Gemma Canet Tarrés, Zhe Lin, Zhifei Zhang, Jianming Zhang, Yizhi Song, Dan Ruta, Andrew Gilbert, John Collomosse, Soo Ye Kim：\"*Thinking Outside the BBox: Unconstrained Generative Object Compositing.*\" ECCV (2024) [[pdf]](https://www.ecva.net/papers/eccv_2024/papers_ECCV/papers/07965.pdf)\n+ Weijing Tao, Xiaofeng Yang, Biwen Lei, Miaomiao Cui, Xuansong Xie, Guosheng Lin: \"*MotionCom: Automatic and Motion-Aware Image Composition with LLM and Video Diffusion Prior.*\" arXiv preprint arXiv:2409.10090 (2024) [[arXiv]](https://arxiv.org/pdf/2409.10090.pdf) [[code]](https://github.com/weijing-tao/MotionCom)\n+ Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, He Zhang, Wei Xiong, Daniel Aliaga: \"*IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation.*\" CVPR (2024) [[pdf]](https://openaccess.thecvf.com/content/CVPR2024/papers/Song_IMPRINT_Generative_Object_Compositing_by_Learning_Identity-Preserving_Representation_CVPR_2024_paper.pdf)\n+ Xi Chen, Lianghua Huang, Yu Liu, Yujun Shen, Deli Zhao, Hengshuang Zhao: \"*AnyDoor: Zero-shot Object-level Image Customization.*\" CVPR (2024) [[pdf]](https://openaccess.thecvf.com/content/CVPR2024/papers/Chen_AnyDoor_Zero-shot_Object-level_Image_Customization_CVPR_2024_paper.pdf) [[code]](https://github.com/damo-vilab/AnyDoor) [[demo]](https://huggingface.co/spaces/xichenhku/AnyDoor-online)\n+ Vishnu Sarukkai, Linden Li, Arden Ma, Christopher Re, Kayvon Fatahalian: \"*Collage Diffusion.*\" WACV (2024) [[pdf]](https://openaccess.thecvf.com/content/WACV2024/papers/Sarukkai_Collage_Diffusion_WACV_2024_paper.pdf) [[code]](https://github.com/VSAnimator/collage-diffusion) \n+ Ziyang Yuan, Mingdeng Cao, Xintao Wang, Zhongang Qi, Chun Yuan, Ying Shan: \"*CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models.*\" ACM MM (2024) [[pdf]](https://dl.acm.org/doi/pdf/10.1145/3664647.3681396) [[code]](https://github.com/TencentARC/CustomNet) [[demo]](https://huggingface.co/spaces/TencentARC/CustomNet)\n+ Bo Zhang, Yuxuan Duan, Jun Lan, Yan Hong, Huijia Zhu, Weiqiang Wang, Li Niu: \"*ControlCom: Controllable Image Composition using Diffusion Model.*\" arXiv preprint arXiv:2308.10040 (2023) [[arXiv]](https://arxiv.org/pdf/2308.10040.pdf) [[code]](https://github.com/bcmi/ControlCom-Image-Composition) [[demo]](https://bcmi.sjtu.edu.cn/home/niuli/demo_image_composition/)\n+ Xin Zhang, Jiaxian Guo, Paul Yoo, Yutaka Matsuo, Yusuke Iwasawa: \"*Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model.*\" arXiv preprint arXiv:2306.07596 (2023) [[arXiv]](https://arxiv.org/pdf/2306.07596.pdf) [[code]](https://sites.google.com/view/phd-demo-page)\n+ Binxin Yang, Shuyang Gu, Bo Zhang, Ting Zhang, Xuejin Chen, Xiaoyan Sun, Dong Chen, Fang Wen: \"*Paint by Example: Exemplar-based Image Editing with Diffusion Models.*\" CVPR (2023) [[arXiv]](https://arxiv.org/pdf/2211.13227.pdf) [[code]](https://arxiv.org/pdf/2211.13227.pdf) [[demo]](https://huggingface.co/spaces/Fantasy-Studio/Paint-by-Example)\n+ Yizhi Song, Zhifei Zhang, Zhe Lin, Scott Cohen, Brian Price, Jianming Zhang, Soo Ye Kim, Daniel Aliaga: \"*ObjectStitch: Generative Object Compositing.*\" CVPR (2023) [[arXiv]](https://arxiv.org/pdf/2212.00932.pdf) [[code]](https://github.com/bcmi/ObjectStitch-Image-Composition)\n+ Sumith Kulal, Tim Brooks, Alex Aiken, Jiajun Wu, Jimei Yang, Jingwan Lu, Alexei A. Efros, Krishna Kumar Singh: \"*Putting People in Their Place: Affordance-Aware Human Insertion into Scenes.*\" CVPR (2023) [[paper]](https://sumith1896.github.io/affordance-insertion/static/paper/affordance_insertion_cvpr2023.pdf) [[code]](https://github.com/adobe-research/affordance-insertion)\n+ Lingxiao Lu, Bo Zhang, Li Niu: \"*DreamCom: Finetuning Text-guided Inpainting Model for Image Composition.*\" arXiv preprint arXiv:2309.15508 (2023) [[arXiv]](https://arxiv.org/pdf/2309.15508.pdf) [[code]](https://github.com/bcmi/DreamCom-Image-Composition)\n+ Tianle Li, Max Ku, Cong Wei, Wenhu Chen: \"*DreamEdit: Subject-driven Image Editing.*\" TMLR (2023) [[arXiv]](https://arxiv.org/pdf/2306.12624.pdf) [[code]](https://github.com/DreamEditBenchTeam/DreamEdit)\n\n\n\n## Other Resources\n\n+ [Awesome-Image-Composition](https://github.com/bcmi/Awesome-Object-Insertion)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbcmi%2FAwesome-Generative-Image-Composition","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbcmi%2FAwesome-Generative-Image-Composition","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbcmi%2FAwesome-Generative-Image-Composition/lists"}