Papers › IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

13 Aug 2023arXiv:2308.06721archive 2025-07-28

Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, Wei Yang

Recent years have witnessed the strong power of large text-to-image diffusion models for the impressive generative capability to create high-fidelity images. However, it is very tricky to generate desired images using only text prompt as it often involves complex prompt engineering. An alternative to text prompt is image prompt, as the saying goes: "an image is worth a thousand words". Although existing methods of direct fine-tuning from pretrained models are effective, they require large computing resources and are not compatible with other base models, text prompt, and structural controls. In this paper, we present IP-Adapter, an effective and lightweight adapter to achieve image prompt capability for the pretrained text-to-image diffusion models. The key design of our IP-Adapter is decoupled cross-attention mechanism that separates cross-attention layers for text features and image features. Despite the simplicity of our method, an IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fully fine-tuned image prompt model. As we freeze the pretrained diffusion model, the proposed IP-Adapter can be generalized not only to other custom models fine-tuned from the same base model, but also to controllable generation using existing controllable tools. With the benefit of the decoupled cross-attention strategy, the image prompt can also work well with the text prompt to achieve multimodal image generation. The project page is available at https://ip-adapter.github.io.

PaperPDFCodeCode Syntology ran

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 8 code samples harvested from 1 repository linked to this paper: 8 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; 7 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 1 repository, 8 ran (1 with no instrument failure; 7 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

fhshen2022/prunerepaint mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Visual Saliency Transformer (arXiv:2104.12099; that paper's own run record: 7 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
liuxiaoyu1104/smartcontrol mentioned on GitHubpytorchSyntology: not harvested report
tencent-ailab/ip-adapter mentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 8 ran (7 instrument-failed) · 0 unverified report
mindspore-lab/mindone mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested 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

8 samples harvested: 8 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; 7 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
1ran; the contract check could not run
1ran

Licence: 7 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from tencent-ailab/ip-adapter. “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”. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

tencent-ailab/ip-adapter community (archive-listed) 8 samples, 8 ran (7 instrument-failed) · 0 unverified
FeedForward in 198 papers ip_adapter/resampler.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 5105747c2711b1cb · report fixture: signature dim:int/0/int, mult:int/0/int · returned Sequential · level recorded 2026-09-22
collate_fn in 500 papers tutorial_train.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 01c0e92550c3a1ca · report fixture: signature data:list/1/dict · returned dict · level recorded 2026-09-24
collate_fn in 500 papers tutorial_train_faceid.py ran · our draft was wrong Apache-2.0 (permissive) · 1e0487828d53d63e · report fixture: signature data:list/1/dict · returned dict · level recorded 2026-09-24
hook_fn in 9 papers ip_adapter/utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 06d3e795b3014ef1 · report fixture: signature name:str/0/str · returned function · level recorded 2026-09-25
masked_mean in 74 papers
census: 8 implementations from 11 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
ip_adapter/resampler.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 230588e8f1237737 · report fixture: signature t:Tensor/3/float, dim:int/0/int, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-25
register_cross_attention_hook in 7 papers ip_adapter/utils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · cf95fb65ebfe64b4 · report fixture: signature unet:callable/0/? · returned MockUNet · level recorded 2026-09-25
reshape_tensor in 31 papers ip_adapter/resampler.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 4cb2e2a2ca0bec9f · report fixture: signature x:Tensor/3/float, heads:int/0/int · returned Tensor · level recorded 2026-09-25
upscale in 13 papers ip_adapter/utils.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 25837bff8f005465 · report fixture: signature attn_map:Tensor/3/float, target_size:tuple/1/int · returned Tensor · level recorded 2026-09-25

Tasks

Diffusion Personalization Tuning FreeImage GenerationPersonalized Image GenerationPrompt Engineering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Diffusion Personalization Tuning Free AgeDB IP-Adapter-FaceID-Plus Cosine Similarity 0.600 #3 of 7 Archive leaderboard report
Diffusion Personalization Tuning Free AgeDB IP-Adapter-FaceID-Plus FID 11.817 #3 of 7 Archive leaderboard report
Diffusion Personalization Tuning Free AgeDB IP-Adapter-FaceID-Plus LPIPS 0.384 #3 of 7 Archive leaderboard report
Diffusion Personalization Tuning Free AgeDB IP-Adapter-FaceID-PlusV2 Cosine Similarity 0.572 #4 of 7 Archive leaderboard report
Diffusion Personalization Tuning Free AgeDB IP-Adapter-FaceID-PlusV2 FID 10.798 #4 of 7 Archive leaderboard report
Diffusion Personalization Tuning Free AgeDB IP-Adapter-FaceID-PlusV2 LPIPS 0.429 #4 of 7 Archive leaderboard report
Diffusion Personalization Tuning Free AgeDB IP-Adapter-FaceID (SDXL) Cosine Similarity 0.535 #5 of 7 Archive leaderboard report
Diffusion Personalization Tuning Free AgeDB IP-Adapter-FaceID (SDXL) FID 24.105 #5 of 7 Archive leaderboard report
Diffusion Personalization Tuning Free AgeDB IP-Adapter-FaceID (SDXL) LPIPS 0.462 #5 of 7 Archive leaderboard report
Personalized Image Generation DreamBooth IP-Adapter ViT-G SDXL v1.0 Concept Preservation (CP) 0.593 #2 of 7 Archive leaderboard report
Personalized Image Generation DreamBooth IP-Adapter ViT-G SDXL v1.0 Overall (CP * PF) 0.380 #2 of 7 Archive leaderboard report
Personalized Image Generation DreamBooth IP-Adapter ViT-G SDXL v1.0 Prompt Following (PF) 0.640 #2 of 7 Archive leaderboard report
Personalized Image Generation DreamBooth IP-Adapter-Plus ViT-H SDXL v1.0 Concept Preservation (CP) 0.833 #5 of 7 Archive leaderboard report
Personalized Image Generation DreamBooth IP-Adapter-Plus ViT-H SDXL v1.0 Overall (CP * PF) 0.344 #5 of 7 Archive leaderboard report
Personalized Image Generation DreamBooth IP-Adapter-Plus ViT-H SDXL v1.0 Prompt Following (PF) 0.413 #5 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.

Methods

AdapterBASEDiffusion

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