SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.02252 · 2023

StoryGPT-V: Large Language Models as Consistent Story Visualizers

arXiv · PDF · Open in the Atlas

Code that ran

9 of 15 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 6 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/2312.02252.json · badge: /api/ran/2312.02252.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
xiaoqian-shen/StoryGPT-V canonical (classifier label)
classifier basis: census
9 ran · 6 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran; our contract draft was wrong, not the code
xiaoqian-shen/StoryGPT-V/models/data.py
pointer only (licence: NONE) · get_code("a3b4f58d84032797")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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.

contrastive_loss Ran
ran; our contract draft was wrong, not the code
xiaoqian-shen/StoryGPT-V/gill/losses.py
pointer only (licence: NONE) · get_code("83ada93fd84968cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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.

find_start_match Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xiaoqian-shen/StoryGPT-V/models/data.py
pointer only (licence: NONE) · get_code("8d1084e28d0e8fb1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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.

get_reg_loss_layer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xiaoqian-shen/StoryGPT-V/models/model.py
pointer only (licence: NONE) · get_code("697ac9abccfd1b93")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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.

get_test_transforms Ran
ran; our contract draft was wrong, not the code
xiaoqian-shen/StoryGPT-V/models/transforms.py
pointer only (licence: NONE) · get_code("addaaf66c3ab7352")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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.

get_train_transforms Ran
ran; our contract draft was wrong, not the code
xiaoqian-shen/StoryGPT-V/models/transforms.py
pointer only (licence: NONE) · get_code("c036796b62b5952d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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.

get_train_transforms_with_segmap Ran
ran; our contract draft was wrong, not the code
xiaoqian-shen/StoryGPT-V/models/transforms.py
pointer only (licence: NONE) · get_code("15ed5aec7f6bd270")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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.

prepare_image_token_idx Ran
ran, honoured the contract we drafted
xiaoqian-shen/StoryGPT-V/models/data.py
pointer only (licence: NONE) · get_code("817e9d69c2cd23d3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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.

stable_diffusion_call_with_references_delayed_conditioning Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
xiaoqian-shen/StoryGPT-V/models/pipeline.py
pointer only (licence: NONE) · get_code("d3c9a29ac1be57e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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.

calculate_activation_statistics Not yet run
unverified (harvested, no recorded run)
xiaoqian-shen/StoryGPT-V/eval/fid_score.py
pointer only (licence: NONE) · get_code("eefbde796616ac35")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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. No invocation recorded.

calculate_frechet_distance Not yet run
unverified (harvested, no recorded run)
xiaoqian-shen/StoryGPT-V/eval/fid_score.py
pointer only (licence: NONE) · get_code("b71963b3facc5fb5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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. No invocation recorded.

fuse_object_embeddings Not yet run
unverified (harvested, no recorded run)
xiaoqian-shen/StoryGPT-V/models/model.py
pointer only (licence: NONE) · get_code("2fa8e59bc1db947b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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. No invocation recorded.

l1_loss Not yet run
unverified (harvested, no recorded run)
xiaoqian-shen/StoryGPT-V/gill/losses.py
pointer only (licence: NONE) · get_code("7f4dc018c6466fcc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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. No invocation recorded.

l2_loss Not yet run
unverified (harvested, no recorded run)
xiaoqian-shen/StoryGPT-V/gill/losses.py
pointer only (licence: NONE) · get_code("f04280cd71a46d32")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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. No invocation recorded.

unet_store_cross_attention_scores Not yet run
unverified (harvested, no recorded run)
xiaoqian-shen/StoryGPT-V/models/model.py
pointer only (licence: NONE) · get_code("0a5a54048f832e12")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiaoqian-shen/StoryGPT-V 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. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 10 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 the same month, 8 later) and 5 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
contrastive_loss 3 other papers
1 dated earlier, 2 later
2301.13823 (2023-01)
Grounding Language Models to Images for Multimodal Inputs and Outputs
2402.18695 (2024-02)
Grounding Language Models for Visual Entity Recognition
2602.19146 (2026-02)
VIGiA: Instructional Video Guidance via Dialogue Reasoning and Retrieval
fuse_object_embeddings 3 other papers
2 dated earlier, 1 later
2305.10431 (2023-05)
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
2311.10329 (2023-11)
High-fidelity Person-centric Subject-to-Image Synthesis
get_test_transforms 3 other papers
2 dated earlier, 1 later
2305.10431 (2023-05)
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
2311.10329 (2023-11)
High-fidelity Person-centric Subject-to-Image Synthesis
get_train_transforms 3 other papers
2 dated earlier, 1 later
2305.10431 (2023-05)
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
2311.10329 (2023-11)
High-fidelity Person-centric Subject-to-Image Synthesis
get_train_transforms_with_segmap 3 other papers
2 dated earlier, 1 later
2305.10431 (2023-05)
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
2311.10329 (2023-11)
High-fidelity Person-centric Subject-to-Image Synthesis
prepare_image_token_idx 3 other papers
2 dated earlier, 1 later
2305.10431 (2023-05)
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
2311.10329 (2023-11)
High-fidelity Person-centric Subject-to-Image Synthesis
unet_store_cross_attention_scores 3 other papers
2 dated earlier, 1 later
2305.10431 (2023-05)
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention
2311.10329 (2023-11)
High-fidelity Person-centric Subject-to-Image Synthesis
l2_loss 2 other papers
2 later
2404.18202 (2024-04)
WorldGPT: Empowering LLM as Multimodal World Model
2502.18364 (2025-02)
ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation
calculate_frechet_distance 1 other paper
1 dated earlier
2105.10026 (2021-05)
Improving Generation and Evaluation of Visual Stories via Semantic Consistency
stable_diffusion_call_with_references_delayed_conditioning 1 other paper
1 dated earlier
2305.10431 (2023-05)
FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention

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 generative models have demonstrated impressive capabilities in generating realistic and visually pleasing images grounded on textual prompts. Nevertheless, a significant challenge remains in applying these models for the more intricate task of story visualization. Since it requires resolving pronouns (he, she, they) in the frame descriptions, i.e., anaphora resolution, and ensuring consistent characters and background synthesis across frames. Yet, the emerging Large Language Model (LLM) showcases robust reasoning abilities to navigate through ambiguous references and process extensive sequences. Therefore, we introduce \emph{StoryGPT-V}, which leverages the merits of the latent diffusion (LDM) and LLM to produce images with consistent and high-quality characters grounded on given story descriptions. First, we train a character-aware LDM, which takes character-augmented semantic embedding as input and includes the supervision of the cross-attention map using character segmentation masks, aiming to enhance character generation accuracy and faithfulness. In the second stage, we enable an alignment between the output of LLM and the character-augmented embedding residing in the input space of the first-stage model. This harnesses the reasoning ability of LLM to address ambiguous references and the comprehension capability to memorize the context. We conduct comprehensive experiments on two visual story visualization benchmarks. Our model reports superior quantitative results and consistently generates accurate characters of remarkable quality with low memory consumption. Our code is publicly available at: \href{https://xiaoqian-shen.github.io/StoryGPT-V}{https://xiaoqian-shen.github.io/StoryGPT-V}.

For agents

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

get_harvested_code_for_paper("2312.02252")
get_code_for_paper("2312.02252")
have("2312.02252")

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

curl https://syntology.ai/api/ran/2312.02252.json

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

[![Syntology run record](https://syntology.ai/api/ran/2312.02252.svg)](https://syntology.ai/paper/2312.02252)

Connect an agent — have() is free.