Papers › An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

2 Aug 2022arXiv:2208.01618archive 2025-07-28

Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H. Bermano, Gal Chechik, Daniel Cohen-Or

Text-to-image models offer unprecedented freedom to guide creation through natural language. Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes. In other words, we ask: how can we use language-guided models to turn our cat into a painting, or imagine a new product based on our favorite toy? Here we present a simple approach that allows such creative freedom. Using only 3-5 images of a user-provided concept, like an object or a style, we learn to represent it through new "words" in the embedding space of a frozen text-to-image model. These "words" can be composed into natural language sentences, guiding personalized creation in an intuitive way. Notably, we find evidence that a single word embedding is sufficient for capturing unique and varied concepts. We compare our approach to a wide range of baselines, and demonstrate that it can more faithfully portray the concepts across a range of applications and tasks. Our code, data and new words will be available at: https://textual-inversion.github.io

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 5 repositories linked to this paper: 10 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 9 samples from 4 repositories, 7 ran (5 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

rinongal/textual_inversion officialmentioned on GitHubpytorchSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
brandontrabucco/da-fusion mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Effective Data Augmentation With Diffusion Models (arXiv:2302.07944; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
cloneofsimo/lora mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (2 instrument-failed) · 0 unverified report
giannisdaras/multires_textual_inversion mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multiresolution Textual Inversion (arXiv:2211.17115; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
ignoww/ZOODiP mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
joycenerd/p4d mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
nicolai256/stable-textual-inversion_win mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
visinf/diagen mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DIAGen: Diverse Image Augmentation with Generative Models (arXiv:2408.14584; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
yandex-research/dvar mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics (arXiv:2302.04841; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

13 samples harvested: 10 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
3ran · our draft was wrong
4ran
3unverified

Licence: 1 of the 13 samples is 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 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

rinongal/textual_inversion official repository 4 samples, 3 ran (1 instrument-failed) · 1 unverified
get_bert_token_for_string in 14 papers ldm/modules/embedding_manager.py ran · honoured contract MIT (permissive) · d5726f9e3a5684c3 · report fixture: signature tokenizer:callable/0/?, string:str/0/str · returned Tensor · level recorded 2026-09-22
get_clip_token_for_string in 16 papers ldm/modules/embedding_manager.py ran · honoured contract MIT (permissive) · 41c6eb3a0aa3eb46 · report fixture: signature tokenizer:callable/0/?, string:str/0/str · returned Tensor · level recorded 2026-09-22
get_embedding_for_clip_token in 13 papers ldm/modules/embedding_manager.py ran · our draft was wrong MIT (permissive) · 71c2df28a1008d03 · report fixture: signature embedder:callable/0/?, token:Tensor/1/float · returned Tensor · level recorded 2026-09-22
EmbeddingManager ldm/modules/embedding_manager.py unverified MIT (permissive) · 7cb89a6737441411 · report
cloneofsimo/lora community (archive-listed) 4 samples, 4 ran (2 instrument-failed) · 0 unverified
LoraInjectedConv2d lora_diffusion/lora.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 1548fd8499deb498 · report fixture: returned LoraInjectedConv2d · level recorded 2026-09-22
LoraInjectedLinear lora_diffusion/lora.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 3ca96bc3c5f38318 · report fixture: returned LoraInjectedLinear · level recorded 2026-09-22
_find_modules_v2 lora_diffusion/lora.py ran · our draft was wrong Apache-2.0 (permissive) · e1b3ccc792ff8565 · report fixture: signature model:callable/0/?, ancestor_class:NoneType/0/?, search_class:list/1/callable, exclude_children_of:list/1/callable · returned generator · level recorded 2026-09-22
inject_trainable_lora in 12 papers lora_diffusion/lora.py ran · our draft was wrong Apache-2.0 (permissive) · c8dd7e385ef5e915 · report fixture: signature model:callable/0/?, target_replace_module:set/0/?, r:int/0/int, loras:NoneType/0/?, verbose:bool/0/bool, dropout_p:float/0/float, scale:float/0/float · returned tuple · level recorded 2026-09-22
ignoww/ZOODiP community (archive-listed) 1 sample, 0 ran · 1 unverified
TextualInversionDataset train_zoodip.py unverified no licence file found · pointer only · 0c65f0063ebd7b8c · report
joycenerd/p4d community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
SimpleTokenizer open_clip/tokenizer.py ran MIT (permissive) · cbc39c2df0771d50 · report fixture: returned SimpleTokenizer · level recorded 2026-09-22
bytes_to_unicode open_clip/tokenizer.py ran · metamorphic tier: deterministic MIT (permissive) · 5267c9a6cdeea45b · report fixture: returned dict · level recorded 2026-09-22
nicolai256/stable-textual-inversion_win community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
get_clip_token_for_string in 16 papers ldm/modules/embedding_manager.py ran · honoured contract MIT (permissive) · 7e334d1575bdaede · report fixture: signature tokenizer:callable/0/?, string:str/0/str · returned Tensor · level recorded 2026-09-24
EmbeddingManager ldm/modules/embedding_manager.py unverified MIT (permissive) · e7e48e96a6442923 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

5 assemblies on this paper: 5 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

5 sibling assemblies for Textual Inversion (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Textual Inversion (graph method: Textual Inversion). 6 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. SimpleTokenizer entry · level 1 · ran · cbc39c2df0771d50
  2. basic_clean helper · level 1 · ran · our draft was wrong · 98f385d847636a3e
  3. bytes_to_unicode helper · level 1 · ran · 5267c9a6cdeea45b
  4. default_bpe helper · level 1 · ran · c032e98969097964
  5. get_pairs helper · level 1 · ran · our draft was wrong · d919ae32e5e4e616
  6. whitespace_clean helper · level 1 · ran · our draft was wrong · 9542161e9640b858

harvested Assembly for Textual Inversion (graph method: Textual Inversion). 4 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. inject_trainable_lora entry · level 1 · ran · our draft was wrong · c8dd7e385ef5e915
  2. LoraInjectedLinear model · level 1 · ran · 3ca96bc3c5f38318
  3. LoraInjectedConv2d model · level 1 · ran · 1548fd8499deb498
  4. _find_modules_v2 helper · level 1 · ran · our draft was wrong · e1b3ccc792ff8565

harvested Assembly for Textual Inversion (graph method: Textual Inversion). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. TextualInversionDataset entry · level 0 · unverified · 0c65f0063ebd7b8c

harvested Assembly for Textual Inversion (graph method: Textual Inversion). 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. EmbeddingManager entry · level 0 · unverified · 7cb89a6737441411
  2. get_bert_token_for_string helper · level 1 · ran · honoured contract · d5726f9e3a5684c3
  3. get_clip_token_for_string helper · level 1 · ran · honoured contract · 41c6eb3a0aa3eb46
  4. get_embedding_for_clip_token helper · level 1 · ran · our draft was wrong · 71c2df28a1008d03

harvested Assembly for Textual Inversion (graph method: Textual Inversion). 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. EmbeddingManager entry · level 0 · unverified · e7e48e96a6442923
  2. get_bert_token_for_string helper · level 1 · ran · honoured contract · d5726f9e3a5684c3
  3. get_clip_token_for_string helper · level 1 · ran · honoured contract · 7e334d1575bdaede
  4. get_embedding_for_clip_token helper · level 1 · ran · our draft was wrong · 71c2df28a1008d03

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2208.01618") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image GenerationPersonalized Image GenerationText to Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Personalized Image Generation DreamBooth Textual Inversion SD v1.5 Concept Preservation (CP) 0.378 #7 of 7 Archive leaderboard report
Personalized Image Generation DreamBooth Textual Inversion SD v1.5 Overall (CP * PF) 0.236 #7 of 7 Archive leaderboard report
Personalized Image Generation DreamBooth Textual Inversion SD v1.5 Prompt Following (PF) 0.624 #7 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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