Papers › GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

20 Dec 2021arXiv:2112.10741archive 2025-07-28

Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, Mark Chen

Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity. We explore diffusion models for the problem of text-conditional image synthesis and compare two different guidance strategies: CLIP guidance and classifier-free guidance. We find that the latter is preferred by human evaluators for both photorealism and caption similarity, and often produces photorealistic samples. Samples from a 3.5 billion parameter text-conditional diffusion model using classifier-free guidance are favored by human evaluators to those from DALL-E, even when the latter uses expensive CLIP reranking. Additionally, we find that our models can be fine-tuned to perform image inpainting, enabling powerful text-driven image editing. We train a smaller model on a filtered dataset and release the code and weights at https://github.com/openai/glide-text2im.

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 15 code samples harvested from 1 repository linked to this paper: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 9 ran (8 with no instrument failure; 1 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 1 of its repositories that Syntology harvested for other papers:

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.

openai/glide-text2im officialmentioned in papermentioned on GitHubpytorchSyntology: 15 samples, 9 ran (1 instrument-failed) · 6 unverified report
ermongroup/SDEdit mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations (arXiv:2108.01073; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified) and Diffusion Models for Adversarial Purification (arXiv:2205.07460; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 4 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 7 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

15 samples harvested: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 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.

1ran · our draft was wrong
8ran
6unverified

Licence: 0 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 openai/glide-text2im. “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.

openai/glide-text2im official repository 15 samples, 9 ran (1 instrument-failed) · 6 unverified
GroupNorm32 in 11 papers glide_text2im/text2im_model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · afad4c14b97816a5 · report fixture: returned GroupNorm32 · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
glide_text2im/text2im_model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · b4ca43deda023234 · report fixture: returned LayerNorm · level recorded 2026-09-22
MLP in 375 papers glide_text2im/text2im_model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 1df304371337469d · report fixture: returned MLP · level recorded 2026-09-22
MultiheadAttention in 44 papers glide_text2im/text2im_model.py ran · metamorphic tier: deterministic MIT (permissive) · 001daee6f2379723 · report fixture: returned MultiheadAttention · level recorded 2026-09-22
QKVAttention in 25 papers glide_text2im/text2im_model.py ran MIT (permissive) · 84ffe49eed5f64f8 · report fixture: signature qkv:Tensor/3/float, encoder_kv:Tensor/3/float · returned Tensor · level recorded 2026-09-24
QKVMultiheadAttention glide_text2im/text2im_model.py ran · metamorphic tier: deterministic MIT (permissive) · be1f454b2f7a88fc · report fixture: returned QKVMultiheadAttention · level recorded 2026-09-22
ResidualAttentionBlock in 38 papers glide_text2im/text2im_model.py ran · metamorphic tier: deterministic MIT (permissive) · 240a712d20a01f00 · report fixture: returned ResidualAttentionBlock · level recorded 2026-09-22
Transformer in 173 papers glide_text2im/text2im_model.py ran · metamorphic tier: deterministic MIT (permissive) · d67f9d0e7ed82f5f · report fixture: returned Transformer · level recorded 2026-09-22
normalization in 70 papers
census: 4 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
glide_text2im/text2im_model.py ran · our draft was wrong MIT (permissive) · c93ddadd4581c6e6 · report fixture: signature channels:int/0/int, swish:float/0/float · returned GroupNorm32 · level recorded 2026-09-22
AttentionBlock in 69 papers glide_text2im/text2im_model.py unverified MIT (permissive) · 267115dc63f308a8 · report
Text2ImUNet glide_text2im/text2im_model.py unverified MIT (permissive) · e25a725bbd980bac · report
TimestepEmbedSequential in 28 papers glide_text2im/text2im_model.py unverified MIT (permissive) · ebfd51a2d88f9da8 · report
UNetModel in 23 papers glide_text2im/text2im_model.py unverified MIT (permissive) · e28a6df0e478f28e · report
convert_module_to_f16 glide_text2im/text2im_model.py unverified MIT (permissive) · 503bb7076a4bd667 · 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 GLIDE (graph method: GLIDE). 24 bricks; individually on a fixture: 14 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. Text2ImUNet entry · level 0 · unverified · e25a725bbd980bac
  2. LayerNorm helper · level 1 · ran · b4ca43deda023234
  3. Transformer model · level 1 · ran · d67f9d0e7ed82f5f
  4. UNetModel model · level 0 · unverified · e28a6df0e478f28e
  5. convert_module_to_f16 helper · level 0 · unverified · 503bb7076a4bd667
  6. timestep_embedding helper · level 1 · ran · our draft was wrong · 88867f4df8cef2a9
  7. ResidualAttentionBlock helper · level 1 · ran · 240a712d20a01f00
  8. AttentionBlock model · level 0 · unverified · 267115dc63f308a8
  9. Downsample helper · level 1 · ran · 8c5676227adb2492
  10. ResBlock model · level 0 · unverified · 86554561a414fdb7
  11. TimestepEmbedSequential model · level 0 · unverified · ebfd51a2d88f9da8
  12. Upsample helper · level 1 · ran · 6998a3677700ee6c
  13. conv_nd helper · level 0 · unverified · fe4eb545bbb728e0
  14. convert_module_to_f32 helper · level 0 · unverified · b283a8ab305dc007
  15. linear helper · level 1 · ran · our draft was wrong · 0e30585f04efffbe
  16. normalization helper · level 1 · ran · our draft was wrong · c93ddadd4581c6e6
  17. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  18. MLP helper · level 1 · ran · 1df304371337469d
  19. MultiheadAttention helper · level 1 · ran · 001daee6f2379723
  20. QKVAttention helper · level 1 · ran · 84ffe49eed5f64f8
  21. avg_pool_nd helper · level 0 · unverified · ecd0fc28815b65ae
  22. TimestepBlock helper · level 0 · unverified · 7958a01675377ce4
  23. GroupNorm32 helper · level 1 · ran · afad4c14b97816a5
  24. QKVMultiheadAttention helper · level 1 · ran · be1f454b2f7a88fc

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="2112.10741") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DiversityImage GenerationImage InpaintingRerankingText-to-Image GenerationZero-Shot Text-to-Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation COCO (Common Objects in Context) GLIDE (zero-shot) FID 12.24 #31 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

Introduced by this paper: GLIDE

CLIPDiffusionGLIDE

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