Papers › Character-Centric Story Visualization via Visual Planning and Token Alignment

Character-Centric Story Visualization via Visual Planning and Token Alignment

16 Oct 2022arXiv:2210.08465archive 2025-07-28

Hong Chen, Rujun Han, Te-Lin Wu, Hideki Nakayama, Nanyun Peng

Story visualization advances the traditional text-to-image generation by enabling multiple image generation based on a complete story. This task requires machines to 1) understand long text inputs and 2) produce a globally consistent image sequence that illustrates the contents of the story. A key challenge of consistent story visualization is to preserve characters that are essential in stories. To tackle the challenge, we propose to adapt a recent work that augments Vector-Quantized Variational Autoencoders (VQ-VAE) with a text-tovisual-token (transformer) architecture. Specifically, we modify the text-to-visual-token module with a two-stage framework: 1) character token planning model that predicts the visual tokens for characters only; 2) visual token completion model that generates the remaining visual token sequence, which is sent to VQ-VAE for finalizing image generations. To encourage characters to appear in the images, we further train the two-stage framework with a character-token alignment objective. Extensive experiments and evaluations demonstrate that the proposed method excels at preserving characters and can produce higher quality image sequences compared with the strong baselines. Codes can be found in https://github.com/sairin1202/VP-CSV

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

The archive's official repositories (pluslabnlp/vp-csv, sairin1202/vp-csv) were not harvested; the 21 samples below come from 1 repository the archive does not mark official.

Syntology 21 code samples harvested from 1 repository linked to this paper: 12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 21 samples from 1 repository, 12 ran (9 with no instrument failure; 3 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.

pluslabnlp/vp-csv officialmentioned in paperpytorchSyntology: not harvested report
sairin1202/vp-csv officialmentioned in paperpytorchSyntology: 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.

Code Syntology ran Syntology

21 samples harvested: 12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 9 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.

1ran · honoured contract
1ran · our draft was wrong
2ran; the contract check could not run
8ran
9unverified

Licence: 0 of the 21 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 adymaharana/VLCStoryGan. “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. 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.

adymaharana/VLCStoryGan found in paper text by Syntology 21 samples, 12 ran (3 instrument-failed) · 9 unverified
BertEmbeddings in 21 papers vlcgan/model.py ran · metamorphic tier: deterministic MIT (permissive) · 79728760d660d983 · report fixture: returned BertEmbeddings · level recorded 2026-09-22
BertIntermediate in 15 papers vlcgan/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 455739c5ad6b2387 · report fixture: returned BertIntermediate · level recorded 2026-09-22
DynamicFilterLayer vlcgan/model.py ran · metamorphic tier: deterministic MIT (permissive) · a8ea3a32f7622e56 · report fixture: returned DynamicFilterLayer · level recorded 2026-09-22
LxmertAttention vlcgan/model.py ran · metamorphic tier: deterministic MIT (permissive) · 118186316f75b11b · report fixture: returned LxmertAttention · level recorded 2026-09-22
LxmertAttentionOutput vlcgan/model.py ran MIT (permissive) · 37566e964d58aad9 · report fixture: signature hidden_states:Tensor/3/float, input_tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-24
MartPooler vlcgan/model.py ran · metamorphic tier: deterministic MIT (permissive) · f5111c56952b1ddc · report fixture: returned MartPooler · level recorded 2026-09-22
PositionEncoding in 9 papers vlcgan/model.py ran · metamorphic tier: deterministic MIT (permissive) · b6f03dfe01742a92 · report fixture: returned PositionEncoding · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
vlcgan/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · d434aa3ac7f6993a · report fixture: returned ResBlock · level recorded 2026-09-22
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
vlcgan/model.py ran · honoured contract fingerprinted MIT (permissive) · a3abf3fe697fabd0 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
make_pad_shifted_mask vlcgan/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 93af85ca91baf7b0 · report fixture: signature input_mask:Tensor/2/float, max_v_len:int/0/int, max_t_len:int/0/int, memory_len:int/0/int · returned Tensor · level recorded 2026-09-22
make_shifted_mask vlcgan/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · cd0b5f41868c631f · report fixture: signature input_mask:Tensor/2/float, max_v_len:int/0/int, max_t_len:int/0/int, memory_len:int/0/int · returned Tensor · level recorded 2026-09-22
upBlock in 12 papers vlcgan/model.py ran · our draft was wrong MIT (permissive) · 721bc7234edf9845 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int · returned Sequential · level recorded 2026-09-22
BertAttention in 28 papers vlcgan/model.py unverified MIT (permissive) · 7758e2dc60da7479 · report
BertEncoderWithMemory vlcgan/model.py unverified MIT (permissive) · 38a29e27a1641775 · report
BertLayerWithMemory vlcgan/model.py unverified MIT (permissive) · 3b66ce72af6145fa · report
BertSelfAttention in 29 papers vlcgan/model.py unverified MIT (permissive) · e5006dcf91e21556 · report
CA_NET vlcgan/model.py unverified MIT (permissive) · 99751ef923ab069c · report
MemoryUpdater vlcgan/model.py unverified MIT (permissive) · 44aa26a7f2f9a571 · report
NEXT_STAGE_G vlcgan/model.py unverified MIT (permissive) · b72cbd35cd593c73 · report
StoryMartGAN vlcgan/model.py unverified MIT (permissive) · eddb0906b50d313d · report
make_video_only_mask vlcgan/model.py unverified MIT (permissive) · 4b14e2379269d142 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Character-Centric Story Visualization via Visual Planning and Token Alignment (graph method: Character-Centric Story Visualization via Visual Planning and Token Alignment). 27 bricks; individually on a fixture: 18 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. StoryMartGAN entry · level 0 · unverified · eddb0906b50d313d
  2. BertEmbeddings helper · level 1 · ran · 79728760d660d983
  3. BertEncoderWithMemory helper · level 0 · unverified · 38a29e27a1641775
  4. CA_NET model · level 0 · unverified · 99751ef923ab069c
  5. DynamicFilterLayer helper · level 1 · ran · a8ea3a32f7622e56
  6. MartPooler model · level 1 · ran · f5111c56952b1ddc
  7. NEXT_STAGE_G model · level 0 · unverified · b72cbd35cd593c73
  8. conv3x3 helper · level 1 · ran · our draft was wrong · fac5364e2f53c6db
  9. upBlock model · level 1 · ran · our draft was wrong · 721bc7234edf9845
  10. BertLayerNorm helper · level 1 · ran · 72b3695069bfff7f
  11. PositionEncoding helper · level 1 · ran · b6f03dfe01742a92
  12. BertLayerWithMemory helper · level 0 · unverified · 3b66ce72af6145fa
  13. ResBlock model · level 1 · ran · d434aa3ac7f6993a
  14. conv1x1 helper · level 1 · ran · our draft was wrong · 19379807ba70daaa
  15. BertAttention helper · level 0 · unverified · 7758e2dc60da7479
  16. BertIntermediate helper · level 1 · ran · 455739c5ad6b2387
  17. BertOutput helper · level 1 · ran · 5d7bf02e4a7c75a1
  18. BertSelfAttention helper · level 0 · unverified · e5006dcf91e21556
  19. MemoryInitializer helper · level 1 · ran · b51032654d0febc7
  20. MemoryUpdater helper · level 0 · unverified · 44aa26a7f2f9a571
  21. make_pad_shifted_mask helper · level 1 · ran; the contract check could not run (RAISES) · 93af85ca91baf7b0
  22. make_video_only_mask helper · level 0 · unverified · 4b14e2379269d142
  23. BertSelfOutput helper · level 1 · ran · bdf10bafd164be1e
  24. gelu helper · level 1 · ran · honoured contract · a3abf3fe697fabd0
  25. make_shifted_mask helper · level 1 · ran; the contract check could not run (RAISES) · cd0b5f41868c631f
  26. LxmertAttention helper · level 1 · ran · 118186316f75b11b
  27. LxmertAttentionOutput helper · level 1 · ran · 37566e964d58aad9

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="2210.08465") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image GenerationStory VisualizationText to Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

VQ-VAE

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