Papers › Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

23 May 2022arXiv:2205.11487archive 2025-07-28

Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S. Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, Mohammad Norouzi

We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. Imagen builds on the power of large transformer language models in understanding text and hinges on the strength of diffusion models in high-fidelity image generation. Our key discovery is that generic large language models (e.g. T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis: increasing the size of the language model in Imagen boosts both sample fidelity and image-text alignment much more than increasing the size of the image diffusion model. Imagen achieves a new state-of-the-art FID score of 7.27 on the COCO dataset, without ever training on COCO, and human raters find Imagen samples to be on par with the COCO data itself in image-text alignment. To assess text-to-image models in greater depth, we introduce DrawBench, a comprehensive and challenging benchmark for text-to-image models. With DrawBench, we compare Imagen with recent methods including VQ-GAN+CLIP, Latent Diffusion Models, and DALL-E 2, and find that human raters prefer Imagen over other models in side-by-side comparisons, both in terms of sample quality and image-text alignment. See https://imagen.research.google/ for an overview of the results.

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

Syntology 11 code samples harvested from 3 repositories linked to this paper: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 11 samples from 3 repositories, 5 ran (5 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

deep-floyd/if mentioned on GitHubpytorchNOASSERTIONSyntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified report
layer6ai-labs/direct-cms mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples (arXiv:2411.08954; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
teapearce/conditional_diffusion_mnist mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
cene555/Imagen-pytorch pytorchSyntology: 1 sample, 0 ran · 1 unverified report
lucidrains/imagen-pytorch pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tell2Design: A Dataset for Language-Guided Floor Plan Generation (arXiv:2311.15941; that paper's own run record: 24 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 5 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 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 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.

5ran
6unverified

Licence: 9 of the 11 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 3 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.

deep-floyd/if community (archive-listed) 8 samples, 4 ran (0 instrument-failed) · 4 unverified
AttentionPooling in 9 papers deepfloyd_if/model/unet.py ran licence not identified · pointer only · 572c310ea05bf309 · report fixture: returned AttentionPooling · level recorded 2026-09-22
Downsample in 58 papers deepfloyd_if/model/unet.py ran fingerprinted licence not identified · pointer only · 93058e5e24fa4d4a · report fixture: returned Downsample · level recorded 2026-09-22
QKVAttention in 25 papers deepfloyd_if/model/unet.py ran licence not identified · pointer only · c024083e30c5368d · report fixture: returned QKVAttention · level recorded 2026-09-22
Upsample in 77 papers deepfloyd_if/model/unet.py ran fingerprinted licence not identified · pointer only · 4f1ccffbc59c4bbe · report fixture: returned Upsample · level recorded 2026-09-22
AttentionBlock in 69 papers deepfloyd_if/model/unet.py unverified licence not identified · pointer only · 83356f082da409f5 · report
TimestepEmbedSequential in 28 papers deepfloyd_if/model/unet.py unverified licence not identified · pointer only · 79ba2446de89789e · report
UNetModel in 23 papers deepfloyd_if/model/unet.py unverified licence not identified · pointer only · c27dfab7177fdf2b · report
teapearce/conditional_diffusion_mnist community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
UnetDown in 5 papers script.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · c1a53d10c7cfa17e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ContextUnet script.py unverified MIT (permissive) · 156e412579f74583 · report
cene555/Imagen-pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
Text2ImUNet imagen_pytorch/text2im_model.py unverified no licence file found · pointer only · 7fcd4eb74a12867c · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Imagen (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Imagen (graph method: Imagen). 18 bricks; individually on a fixture: 8 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; 4 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. Text2ImUNet entry · level 0 · unverified · 7fcd4eb74a12867c
  2. UNetModel model · level 0 · unverified · e28a6df0e478f28e
  3. timestep_embedding helper · level 1 · ran · our draft was wrong · 88867f4df8cef2a9
  4. AttentionBlock model · level 0 · unverified · 267115dc63f308a8
  5. Downsample helper · level 1 · ran · 8c5676227adb2492
  6. ResBlock model · level 0 · unverified · 86554561a414fdb7
  7. TimestepEmbedSequential helper · level 0 · unverified · ebfd51a2d88f9da8
  8. Upsample helper · level 1 · ran · 6998a3677700ee6c
  9. conv_nd helper · level 0 · unverified · fe4eb545bbb728e0
  10. convert_module_to_f16 helper · level 0 · unverified · 503bb7076a4bd667
  11. convert_module_to_f32 helper · level 0 · unverified · b283a8ab305dc007
  12. linear helper · level 1 · ran · our draft was wrong · 0e30585f04efffbe
  13. normalization helper · level 1 · ran · our draft was wrong · c93ddadd4581c6e6
  14. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  15. QKVAttention model · level 1 · ran · 84ffe49eed5f64f8
  16. avg_pool_nd helper · level 0 · unverified · ecd0fc28815b65ae
  17. TimestepBlock helper · level 0 · unverified · 7958a01675377ce4
  18. GroupNorm32 helper · level 1 · ran · afad4c14b97816a5

harvested Assembly for Imagen (graph method: Imagen). 20 bricks; individually on a fixture: 13 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. UNetModel entry · level 0 · unverified · c27dfab7177fdf2b
  2. AttentionBlock model · level 0 · unverified · 83356f082da409f5
  3. AttentionPooling helper · level 1 · ran · 572c310ea05bf309
  4. Downsample model · level 1 · ran · 93058e5e24fa4d4a
  5. ResBlock model · level 0 · unverified · 9878524ba095b65b
  6. TimestepEmbedSequential model · level 0 · unverified · 79ba2446de89789e
  7. Upsample model · level 1 · ran · 4f1ccffbc59c4bbe
  8. conv_nd helper · level 0 · unverified · fe4eb545bbb728e0
  9. get_activation helper · level 1 · ran · our draft was wrong · f69b4b4a037d5c42
  10. linear helper · level 1 · ran · our draft was wrong · 0e30585f04efffbe
  11. normalization helper · level 1 · ran · our draft was wrong · 8337c76a7f90e95b
  12. timestep_embedding helper · level 1 · ran · our draft was wrong · 6b0b644d0ca2f8c5
  13. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  14. QKVAttention model · level 1 · ran · c024083e30c5368d
  15. avg_pool_nd helper · level 0 · unverified · ecd0fc28815b65ae
  16. TimestepBlock helper · level 0 · unverified · 40fb9bc947892adc
  17. GELUJit helper · level 1 · ran · 86ea32679c0b2d1a
  18. GroupNorm32 helper · level 1 · ran · 1e4248a187aac2d8
  19. gelu_jit helper · level 1 · ran; the contract check could not run · cd23a508b079e2d4
  20. gelu helper · level 1 · ran · our draft was wrong · f51cf2cbd3e598d8

harvested Assembly for Imagen (graph method: Imagen). 5 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. ContextUnet entry · level 0 · unverified · 156e412579f74583
  2. EmbedFC model · level 1 · ran · db6eecd6a0d6e2ab
  3. ResidualConvBlock helper · level 1 · ran · 622391c84a43b104
  4. UnetDown helper · level 1 · ran · c1a53d10c7cfa17e
  5. UnetUp helper · level 0 · unverified · 54b6bfed3b95b9a3

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="2205.11487") returns these assemblies with each brick's role and wiring (how to connect).

Datasets

Introduced by this paper, per the archive.

DrawBench

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation COCO (Common Objects in Context) Imagen (zero-shot) FID 7.27 #15 of 69 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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