Papers › Key-Locked Rank One Editing for Text-to-Image Personalization

Key-Locked Rank One Editing for Text-to-Image Personalization

2 May 2023arXiv:2305.01644archive 2025-07-28

Yoad Tewel, Rinon Gal, Gal Chechik, Yuval Atzmon

Text-to-image models (T2I) offer a new level of flexibility by allowing users to guide the creative process through natural language. However, personalizing these models to align with user-provided visual concepts remains a challenging problem. The task of T2I personalization poses multiple hard challenges, such as maintaining high visual fidelity while allowing creative control, combining multiple personalized concepts in a single image, and keeping a small model size. We present Perfusion, a T2I personalization method that addresses these challenges using dynamic rank-1 updates to the underlying T2I model. Perfusion avoids overfitting by introducing a new mechanism that "locks" new concepts' cross-attention Keys to their superordinate category. Additionally, we develop a gated rank-1 approach that enables us to control the influence of a learned concept during inference time and to combine multiple concepts. This allows runtime-efficient balancing of visual-fidelity and textual-alignment with a single 100KB trained model, which is five orders of magnitude smaller than the current state of the art. Moreover, it can span different operating points across the Pareto front without additional training. Finally, we show that Perfusion outperforms strong baselines in both qualitative and quantitative terms. Importantly, key-locking leads to novel results compared to traditional approaches, allowing to portray personalized object interactions in unprecedented ways, even in one-shot settings.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2305.01644")

Code

Syntology Ran 14 of 18 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 13 ran with no contract checked.

By repository: community (archive-listed): 18 samples from 1 repository, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested; 14 ran; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
13ran
4unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

analytic_kernel ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/ldm/modules/image_degradation/bsrgan.py community (archive-listed) ran fingerprinted MIT (permissive) · b04722a19845dc90 · report
anisotropic_Gaussian ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/ldm/modules/image_degradation/bsrgan.py community (archive-listed) ran MIT (permissive) · 5a0ca1bba88bb4b0 · report
clip_load_untrained ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/models/clipseg.py community (archive-listed) ran MIT (permissive) · 5b4a0a0fc3e2a388 · report
cosine_warmup_lr ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/training.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 057d183d358d1e9a · report
denorm ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/evaluation_utils.py community (archive-listed) ran MIT (permissive) · 17efe0b1bfd9f343 · report
fast_iou_curve ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/evaluation_utils.py community (archive-listed) ran MIT (permissive) · e1d523a6f8c92026 · report
filter_args ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/general_utils.py community (archive-listed) ran MIT (permissive) · febf3c4380082c74 · report
get_attribute ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/general_utils.py community (archive-listed) ran MIT (permissive) · c35bef083a3a63d9 · report
get_image_paths ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/ldm/modules/image_degradation/utils_image.py community (archive-listed) ran MIT (permissive) · f9d4c247328f3337 · report
get_prompt_list ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/models/clipseg.py community (archive-listed) ran MIT (permissive) · f4c0e5f857a103d5 · report
is_image_file ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/ldm/modules/image_degradation/utils_image.py community (archive-listed) ran MIT (permissive) · 226f6afcd57ff476 · report
modcrop_np ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/ldm/modules/image_degradation/bsrgan.py community (archive-listed) ran fingerprinted MIT (permissive) · 04df7487a791a8a1 · report
norm ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/evaluation_utils.py community (archive-listed) ran MIT (permissive) · 151e32d2a7b8134d · report
process_prompts ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/models/vitseg.py community (archive-listed) ran MIT (permissive) · 9ef76f9c72933f80 · report
forward_multihead_attention ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/models/clipseg.py community (archive-listed) unverified MIT (permissive) · 9682702dd7af11cd · report
get_cached_pascal_pfe ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/score.py community (archive-listed) unverified MIT (permissive) · c78a6fe00b0a118f · report
load_model ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/clipseg/general_utils.py community (archive-listed) unverified MIT (permissive) · bca46b85e101b36d · report
patches_from_image ChenDarYen/Key-Locked-Rank-One-Editing-for-Text-to-Image-Personalization/ldm/modules/image_degradation/utils_image.py community (archive-listed) unverified MIT (permissive) · 3984b3ec31e90ef0 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections