{"url":"/task/personalized-image-generation","name":"Personalized Image Generation","slug":"personalized-image-generation","description_markdown":"Utilizes single or multiple images that contain the same subject or style, along with text prompt, to generate images that contain that subject as well as match the textual description. Includes finetuning-based methods (e.g. DreamBooth, Textual Inversion) as well as encoder-based methods (e.g. E4T, ELITE, and IP-Adapter, etc.).","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":58,"papers_with_code":31,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/personalized-image-generation-on-dreambench","slug":"personalized-image-generation-on-dreambench","dataset":"DreamBooth","dataset_url":"/dataset/dreambench","rows_in_archive":7,"metrics":["Overall (CP * PF)","Concept Preservation (CP)","Prompt Following (PF)"],"first_row_in_archive_order":{"model":"DreamBooth LoRA SDXL v1.0","paper_title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","paper_url":"/paper/dreambooth-fine-tuning-text-to-image","paper_date":"2022-08-25","arxiv_id":"2208.12242","code_links":[{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/ppdiffusers/examples/dreambooth"},{"title":"XavierXiao/Dreambooth-Stable-Diffusion","url":"https://github.com/XavierXiao/Dreambooth-Stable-Diffusion"},{"title":"cloneofsimo/lora","url":"https://github.com/cloneofsimo/lora"},{"title":"showlab/Tune-A-Video","url":"https://github.com/showlab/Tune-A-Video"},{"title":"zrrskywalker/personalize-sam","url":"https://github.com/zrrskywalker/personalize-sam"},{"title":"google/dreambooth","url":"https://github.com/google/dreambooth"},{"title":"SnailDev/github-hot-hub","url":"https://github.com/SnailDev/github-hot-hub"},{"title":"lonnyzhang423/github-hot-hub","url":"https://github.com/lonnyzhang423/github-hot-hub"},{"title":"yandex-research/dvar","url":"https://github.com/yandex-research/dvar"},{"title":"csguoh/intlora","url":"https://github.com/csguoh/intlora"},{"title":"PrototypeNx/DETEX","url":"https://github.com/PrototypeNx/DETEX"},{"title":"jiahuadong/cifc","url":"https://github.com/jiahuadong/cifc"}],"syntology":{"n":12,"n_ran":10,"n_unverified":2,"n_pointer_only":8}}}],"datasets":[{"url":"/dataset/dreambench","name":"DreamBooth","full_name":"","num_papers_in_archive":523}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":31,"tagged_in_all":58,"items":[{"url":"/paper/dreambooth-fine-tuning-text-to-image","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","date":"2022-08-25","arxiv_id":"2208.12242","repositories_listed":12,"syntology":{"n":12,"n_ran":10,"n_unverified":2,"n_pointer_only":8}},{"url":"/paper/an-image-is-worth-one-word-personalizing-text","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","date":"2022-08-02","arxiv_id":"2208.01618","repositories_listed":9,"syntology":{"n":13,"n_ran":10,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/ip-adapter-text-compatible-image-prompt","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","date":"2023-08-13","arxiv_id":"2308.06721","repositories_listed":4,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/personalized-text-to-image-generation-with","title":"Personalized Text-to-Image Generation with Auto-Regressive Models","date":"2025-04-17","arxiv_id":"2504.13162","repositories_listed":1,"syntology":null},{"url":"/paper/less-to-more-generalization-unlocking-more","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","date":"2025-04-02","arxiv_id":"2504.02160","repositories_listed":1,"syntology":{"n":43,"n_ran":13,"n_unverified":30,"n_pointer_only":0}},{"url":"/paper/conceptrol-concept-control-of-zero-shot","title":"Conceptrol: Concept Control of Zero-shot Personalized Image Generation","date":"2025-03-09","arxiv_id":"2503.06568","repositories_listed":1,"syntology":null},{"url":"/paper/towards-more-accurate-personalized-image","title":"Towards More Accurate Personalized Image Generation: Addressing Overfitting and Evaluation Bias","date":"2025-03-09","arxiv_id":"2503.06632","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-image-generation-with-deep","title":"Personalized Image Generation with Deep Generative Models: A Decade Survey","date":"2025-02-18","arxiv_id":"2502.13081","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-fine-tuning-a-systematic-study-of","title":"Beyond Fine-Tuning: A Systematic Study of Sampling Techniques in Personalized Image Generation","date":"2025-02-09","arxiv_id":"2502.05895","repositories_listed":1,"syntology":null},{"url":"/paper/personamagic-stage-regulated-high-fidelity","title":"PersonaMagic: Stage-Regulated High-Fidelity Face Customization with Tandem Equilibrium","date":"2024-12-20","arxiv_id":"2412.15674","repositories_listed":1,"syntology":null},{"url":"/paper/patchdpo-patch-level-dpo-for-finetuning-free","title":"PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation","date":"2024-12-04","arxiv_id":"2412.03177","repositories_listed":1,"syntology":{"n":11,"n_ran":3,"n_unverified":8,"n_pointer_only":11}},{"url":"/paper/personalized-image-generation-with-large","title":"Personalized Image Generation with Large Multimodal Models","date":"2024-10-18","arxiv_id":"2410.14170","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/facechain-fact-face-adapter-with-decoupled","title":"FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization","date":"2024-10-16","arxiv_id":"2410.12312","repositories_listed":1,"syntology":null},{"url":"/paper/resolving-multi-condition-confusion-for","title":"Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation","date":"2024-09-26","arxiv_id":"2409.17920","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/storymaker-towards-holistic-consistent","title":"StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation","date":"2024-09-19","arxiv_id":"2409.12576","repositories_listed":1,"syntology":null},{"url":"/paper/textboost-towards-one-shot-personalization-of","title":"TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder","date":"2024-09-12","arxiv_id":"2409.08248","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/ezigen-enhancing-zero-shot-subject-driven","title":"EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidance","date":"2024-09-12","arxiv_id":"2409.08091","repositories_listed":1,"syntology":null},{"url":"/paper/dreambench-a-human-aligned-benchmark-for","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","date":"2024-06-24","arxiv_id":"2406.16855","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/rectifid-personalizing-rectified-flow-with","title":"RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance","date":"2024-05-23","arxiv_id":"2405.14677","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/cat-contrastive-adapter-training-for","title":"CAT: Contrastive Adapter Training for Personalized Image Generation","date":"2024-04-11","arxiv_id":"2404.07554","repositories_listed":1,"syntology":null},{"url":"/paper/moma-multimodal-llm-adapter-for-fast","title":"MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation","date":"2024-04-08","arxiv_id":"2404.05674","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":4}},{"url":"/paper/gen4gen-generative-data-pipeline-for","title":"Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition","date":"2024-02-23","arxiv_id":"2402.15504","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/bootpig-bootstrapping-zero-shot-personalized","title":"BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities in Pretrained Diffusion Models","date":"2024-01-25","arxiv_id":"2401.13974","repositories_listed":1,"syntology":null},{"url":"/paper/when-stylegan-meets-stable-diffusion-a-w","title":"When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generative-multimodal-models-are-in-context","title":"Generative Multimodal Models are In-Context Learners","date":"2023-12-20","arxiv_id":"2312.13286","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/when-stylegan-meets-stable-diffusion-a","title":"When StyleGAN Meets Stable Diffusion: a $\\mathscr{W}_+$ Adapter for Personalized Image Generation","date":"2023-11-29","arxiv_id":"2311.17461","repositories_listed":1,"syntology":null},{"url":"/paper/facechain-a-playground-for-identity","title":"FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content","date":"2023-08-28","arxiv_id":"2308.14256","repositories_listed":1,"syntology":null},{"url":"/paper/subject-diffusion-open-domain-personalized","title":"Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning","date":"2023-07-21","arxiv_id":"2307.11410","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/blip-diffusion-pre-trained-subject-1","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","date":"2023-05-24","arxiv_id":"2305.14720","repositories_listed":1,"syntology":null},{"url":"/paper/fastcomposer-tuning-free-multi-subject-image","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","date":"2023-05-17","arxiv_id":"2305.10431","repositories_listed":1,"syntology":{"n":17,"n_ran":6,"n_unverified":11,"n_pointer_only":0}}],"syntology_records":15,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}