Papers › StoryGPT-V: Large Language Models as Consistent Story Visualizers

StoryGPT-V: Large Language Models as Consistent Story Visualizers

4 Dec 2023CVPR 2025 1arXiv:2312.02252archive 2025-07-28

Xiaoqian Shen, Mohamed Elhoseiny

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 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 will be made publicly available.

PaperPDFConference PDFCodeCode 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 15 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 5 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: official repository: 15 samples from 1 repository, 9 ran (3 with no instrument failure; 6 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.

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.

xiaoqian-shen/StoryGPT-V officialmentioned in papermentioned on GitHubpytorchSyntology: 15 samples, 9 ran (6 instrument-failed) · 6 unverified 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.

Code Syntology ran Syntology

15 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 6 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.

1ran · honoured contract
5ran · our draft was wrong
1ran; the contract check could not run
2ran
6unverified

Licence: 15 of the 15 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 xiaoqian-shen/StoryGPT-V. “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.

xiaoqian-shen/StoryGPT-V official repository 15 samples, 9 ran (6 instrument-failed) · 6 unverified
collate_fn in 500 papers models/data.py ran · our draft was wrong no licence file found · pointer only · a3b4f58d84032797 · report fixture: signature examples:list/1/dict · returned dict · level recorded 2026-09-24
contrastive_loss in 80 papers
census: 11 implementations from 18 papers, 7 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32
gill/losses.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 83ada93fd84968cc · report fixture: signature logits:Tensor/2/float · returned Tensor · level recorded 2026-09-22
find_start_match models/data.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 8d1084e28d0e8fb1 · report fixture: signature s1:list/1/int, s2:list/1/int · returned list · level recorded 2026-09-24
get_reg_loss_layer models/model.py ran no licence file found · pointer only · 697ac9abccfd1b93 · report fixture: signature cross_attention_scores:Tensor/3/float, object_segmaps:Tensor/4/float, object_token_idx:Tensor/2/int, object_token_idx_mask:Tensor/2/float, loss_fn:callable/0/? · returned Tensor · level recorded 2026-09-24
get_test_transforms models/transforms.py ran · our draft was wrong no licence file found · pointer only · addaaf66c3ab7352 · report fixture: signature args:Args/0/? · returned Sequential · level recorded 2026-09-24
get_train_transforms in 6 papers models/transforms.py ran · our draft was wrong no licence file found · pointer only · c036796b62b5952d · report fixture: signature args:ArgsConfig/0/? · returned Sequential · level recorded 2026-09-24
get_train_transforms_with_segmap models/transforms.py ran · our draft was wrong no licence file found · pointer only · 15ed5aec7f6bd270 · report fixture: signature args:ArgsConfig/0/? · returned TrainTransformWithSegmap · level recorded 2026-09-24
prepare_image_token_idx models/data.py ran · honoured contract no licence file found · pointer only · 817e9d69c2cd23d3 · report fixture: signature image_token_mask:Tensor/2/bool, max_num_objects:int/0/int · returned tuple · level recorded 2026-09-24
stable_diffusion_call_with_references_delayed_conditioning models/pipeline.py ran no licence file found · pointer only · d3c9a29ac1be57e9 · report fixture: signature self:StableDiffusionPipeline/0/?, prompt:str/0/str, height:NoneType/0/?, width:NoneType/0/?, num_inference_steps:int/0/int, guidance_scale:float/0/float, negative_prompt:NoneType/0/?, num_images_per_prompt:int/0/int, eta:float/0/float, generator:NoneType/0/?, latents:NoneType/0/?, prompt_embeds:Tensor/3/float, prompt_embeds_text_only:Tensor/3/float, negative_prompt_embeds:Tensor/3/float, output_type:str/0/str, return_dict:bool/0/bool, callback:NoneType/0/?, callback_steps:int/0/int, cross_attention_kwargs:NoneType/0/?, start_merge_step:int/0/int · returned StableDiffusionPipelineOutput · level recorded 2026-09-24
calculate_activation_statistics in 75 papers eval/fid_score.py unverified no licence file found · pointer only · eefbde796616ac35 · report
calculate_frechet_distance in 119 papers eval/fid_score.py unverified no licence file found · pointer only · b71963b3facc5fb5 · report
fuse_object_embeddings models/model.py unverified no licence file found · pointer only · 2fa8e59bc1db947b · report
l1_loss in 149 papers
census: 3 implementations from 7 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
gill/losses.py unverified no licence file found · pointer only · 7f4dc018c6466fcc · report
l2_loss in 136 papers gill/losses.py unverified no licence file found · pointer only · f04280cd71a46d32 · report
unet_store_cross_attention_scores models/model.py unverified no licence file found · pointer only · 0a5a54048f832e12 · report

Tasks

Language ModellingLarge Language ModelNavigateStory Visualization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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