Papers › GlyphControl: Glyph Conditional Control for Visual Text Generation

GlyphControl: Glyph Conditional Control for Visual Text Generation

29 May 2023NeurIPS 2023 11arXiv:2305.18259archive 2025-07-28

Yukang Yang, Dongnan Gui, Yuhui Yuan, Weicong Liang, Haisong Ding, Han Hu, Kai Chen

Recently, there has been an increasing interest in developing diffusion-based text-to-image generative models capable of generating coherent and well-formed visual text. In this paper, we propose a novel and efficient approach called GlyphControl to address this task. Unlike existing methods that rely on character-aware text encoders like ByT5 and require retraining of text-to-image models, our approach leverages additional glyph conditional information to enhance the performance of the off-the-shelf Stable-Diffusion model in generating accurate visual text. By incorporating glyph instructions, users can customize the content, location, and size of the generated text according to their specific requirements. To facilitate further research in visual text generation, we construct a training benchmark dataset called LAION-Glyph. We evaluate the effectiveness of our approach by measuring OCR-based metrics, CLIP score, and FID of the generated visual text. Our empirical evaluations demonstrate that GlyphControl outperforms the recent DeepFloyd IF approach in terms of OCR accuracy, CLIP score, and FID, highlighting the efficacy of our method.

PaperPDFConference PDFCodeCode 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

Syntology 9 code samples harvested from 1 repository linked to this paper: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 9 samples from 1 repository, 4 ran (4 with no instrument failure; 0 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.

aigtext/glyphcontrol-release officialmentioned in papermentioned on GitHubpytorchSyntology: 9 samples, 4 ran (0 instrument-failed) · 5 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

9 samples harvested: 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 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.

4ran
5unverified

Licence: 0 of the 9 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 aigtext/glyphcontrol-release. “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.

aigtext/glyphcontrol-release official repository 9 samples, 4 ran (0 instrument-failed) · 5 unverified
CrossAttention in 85 papers cldm/cldm.py ran MIT (permissive) · 8f64e619c23619c5 · report fixture: returned CrossAttention · level recorded 2026-09-22
MemoryEfficientCrossAttention in 7 papers cldm/cldm.py ran MIT (permissive) · 2c8910dba7592809 · report fixture: returned MemoryEfficientCrossAttention · level recorded 2026-09-22
QKVAttention in 25 papers cldm/cldm.py ran MIT (permissive) · 4bed2e5daf64df72 · report fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24
QKVAttentionLegacy in 20 papers cldm/cldm.py ran MIT (permissive) · ba0567fc5b71dbf6 · report fixture: returned QKVAttentionLegacy · level recorded 2026-09-22
AttentionBlock in 69 papers cldm/cldm.py unverified MIT (permissive) · e59c125335cdce0a · report
BasicTransformerBlock in 22 papers cldm/cldm.py unverified MIT (permissive) · c8644b25d74977f2 · report
ControlNet cldm/cldm.py unverified MIT (permissive) · 1e1a7f7b69eb27b1 · report
SpatialTransformer in 23 papers cldm/cldm.py unverified MIT (permissive) · 97e5c1d4532076bf · report
TimestepEmbedSequential in 28 papers cldm/cldm.py unverified MIT (permissive) · 48f3e455f9262eb2 · 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 GlyphControl (graph method: GlyphControl). 29 bricks; individually on a fixture: 18 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. ControlNet entry · level 0 · unverified · 1e1a7f7b69eb27b1
  2. AttentionBlock helper · level 0 · unverified · e59c125335cdce0a
  3. Downsample helper · level 1 · ran · 0feab49c606075bb
  4. ResBlock helper · level 0 · unverified · 6ac534327b50ba98
  5. SpatialTransformer helper · level 0 · unverified · 97e5c1d4532076bf
  6. TimestepEmbedSequential helper · level 0 · unverified · 48f3e455f9262eb2
  7. conv_nd helper · level 0 · unverified · fe4eb545bbb728e0
  8. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  9. linear helper · level 1 · ran · our draft was wrong · 0e30585f04efffbe
  10. timestep_embedding helper · level 1 · ran; the contract check could not run · 9df115707ad18735
  11. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  12. QKVAttention helper · level 1 · ran · 4bed2e5daf64df72
  13. QKVAttentionLegacy helper · level 1 · ran · ba0567fc5b71dbf6
  14. checkpoint helper · level 0 · unverified · c596e50230fd9ed8
  15. normalization helper · level 1 · ran · our draft was wrong · daafc1c89511b8be
  16. avg_pool_nd helper · level 0 · unverified · ecd0fc28815b65ae
  17. TimestepBlock helper · level 0 · unverified · 7958a01675377ce4
  18. Upsample helper · level 1 · ran · 1b4579fe4aec5257
  19. BasicTransformerBlock helper · level 0 · unverified · c8644b25d74977f2
  20. Normalize helper · level 1 · ran · our draft was wrong · c3a6b977022957cb
  21. count_flops_attn helper · level 0 · unverified · 6e9c81a619f204c5
  22. CheckpointFunction helper · level 1 · ran · 70ec8e3dd3981b5e
  23. GroupNorm32 helper · level 1 · ran · 426c2385fa431d9a
  24. CrossAttention helper · level 1 · ran · 8f64e619c23619c5
  25. FeedForward helper · level 1 · ran · 1ce39bf592ba310f
  26. MemoryEfficientCrossAttention helper · level 1 · ran · 2c8910dba7592809
  27. default helper · level 1 · ran · violated contract · 424012cb37b31172
  28. max_neg_value helper · level 1 · ran · our draft was wrong · f2fe51a4a5646c6f
  29. GEGLU helper · level 1 · ran · 387673fa5780bf50

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="2305.18259") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Optical Character Recognition (OCR)Text Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

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