SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.13826 · 2023

Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2301.13826.json · badge: /api/ran/2301.13826.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
AttendAndExcite/Attend-and-Excite canonical (classifier label)
classifier basis not recorded on the link
3 ran · 4 no recorded run
FunctionStatusWhere it lives
get_image_grid Ran
ran; our contract draft was wrong, not the code
AttendAndExcite/Attend-and-Excite/utils/vis_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from I2-Multimedia-Lab/Magnet, is pointer only (licence: NONE) · get_code("0078d117f74b7c20")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from I2-Multimedia-Lab/Magnet, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

show_image_relevance Ran
ran; our contract draft was wrong, not the code
AttendAndExcite/Attend-and-Excite/utils/vis_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from showlab/boxdiff, is pointer only (licence: NONE) · get_code("3c75935b4fdb2c79")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from showlab/boxdiff, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

text_under_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AttendAndExcite/Attend-and-Excite/utils/ptp_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from debottam-dutta7/co3, is pointer only (licence: NONE) · get_code("42f35256bd885673")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from debottam-dutta7/co3, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

aggregate_attention Not yet run
unverified (harvested, no recorded run)
AttendAndExcite/Attend-and-Excite/utils/ptp_utils.py
code served (permissive licence) · get_code("e101acf585a7866f")
How it ran

no invocation recorded.

aggregate_by_full_text Not yet run
unverified (harvested, no recorded run)
AttendAndExcite/Attend-and-Excite/metrics/compute_clip_similarity.py
code served (permissive licence) · get_code("47ea359c386643f7")
How it ran

no invocation recorded.

aggregate_by_min_half Not yet run
unverified (harvested, no recorded run)
AttendAndExcite/Attend-and-Excite/metrics/compute_clip_similarity.py
code served (permissive licence) · get_code("2428b85942ce1cbf")
How it ran

no invocation recorded.

aggregate_text_similarities Not yet run
unverified (harvested, no recorded run)
AttendAndExcite/Attend-and-Excite/metrics/blip_captioning_and_clip_similarity.py
code served (permissive licence) · get_code("20d85a2341dcfcd9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
text_under_image 5 other papers
5 later
2305.16311 (2023-05)
Break-A-Scene: Extracting Multiple Concepts from a Single Image
2307.10816 (2023-07)
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
2307.10864 (2023-07)
Divide & Bind Your Attention for Improved Generative Semantic Nursing
and 2 more not named here
get_image_grid 2 other papers
2 later
2307.10816 (2023-07)
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
2409.19967 (2024-09)
Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function
show_image_relevance 2 other papers
2 later
2307.10816 (2023-07)
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
2409.19967 (2024-09)
Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function
aggregate_attention 1 other paper
1 later
2307.10816 (2023-07)
BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt. While revolutionary, current state-of-the-art diffusion models may still fail in generating images that fully convey the semantics in the given text prompt. We analyze the publicly available Stable Diffusion model and assess the existence of catastrophic neglect, where the model fails to generate one or more of the subjects from the input prompt. Moreover, we find that in some cases the model also fails to correctly bind attributes (e.g., colors) to their corresponding subjects. To help mitigate these failure cases, we introduce the concept of Generative Semantic Nursing (GSN), where we seek to intervene in the generative process on the fly during inference time to improve the faithfulness of the generated images. Using an attention-based formulation of GSN, dubbed Attend-and-Excite, we guide the model to refine the cross-attention units to attend to all subject tokens in the text prompt and strengthen - or excite - their activations, encouraging the model to generate all subjects described in the text prompt. We compare our approach to alternative approaches and demonstrate that it conveys the desired concepts more faithfully across a range of text prompts.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.13826")
get_code_for_paper("2301.13826")
have("2301.13826")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2301.13826.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2301.13826.svg)](https://syntology.ai/paper/2301.13826)

Connect an agent — have() is free.