Papers › Hierarchical Text-Conditional Image Generation with CLIP Latents

Hierarchical Text-Conditional Image Generation with CLIP Latents

13 Apr 2022arXiv:2204.06125archive 2025-07-28

Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, Mark Chen

Contrastive models like CLIP have been shown to learn robust representations of images that capture both semantics and style. To leverage these representations for image generation, we propose a two-stage model: a prior that generates a CLIP image embedding given a text caption, and a decoder that generates an image conditioned on the image embedding. We show that explicitly generating image representations improves image diversity with minimal loss in photorealism and caption similarity. Our decoders conditioned on image representations can also produce variations of an image that preserve both its semantics and style, while varying the non-essential details absent from the image representation. Moreover, the joint embedding space of CLIP enables language-guided image manipulations in a zero-shot fashion. We use diffusion models for the decoder and experiment with both autoregressive and diffusion models for the prior, finding that the latter are computationally more efficient and produce higher-quality samples.

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 38 code samples: 37 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 38: 33 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 3 honoured, 6 violated, 14 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 8 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: community (archive-listed): 37 samples from 4 repositories, 32 ran (22 with no instrument failure; 10 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 6 of the 33 samples that ran have no recorded date.

drboog/Shifted_Diffusion mentioned on GitHubjaxCC0-1.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Shifted Diffusion for Text-to-image Generation (arXiv:2211.15388; that paper's own run record: 13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 1 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
facebookresearch/multimodal mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding (arXiv:2104.12763; that paper's own run record: 7 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified), Align before Fuse: Vision and Language Representation Learning with Momentum Distillation (arXiv:2107.07651; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified), Masked Autoencoders Are Scalable Vision Learners (arXiv:2111.06377; that paper's own run record: 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
harvard-visionlab/lrm-steering mentioned on GitHubpytorchSyntology: 13 samples, 10 ran (1 instrument-failed) · 3 unverified report
kakaobrain/coyo-dataset mentioned on GitHubpytorchSyntology: not harvested report
laion-ai/conditioned-prior mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
liyinqi/un2clip mentioned on GitHubpytorchMITSyntology: 17 samples, 15 ran (8 instrument-failed) · 2 unverified report
woctezuma/steam-CLIP mentioned on GitHubMITSyntology: not harvested report
lucidrains/DALLE2-pytorch pytorchSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 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.

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

38 samples harvested: 33 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 3 honoured, 6 violated, 14 with no contract checked; 10 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
6ran · violated contract
8ran · our draft was wrong
2ran; the contract check could not run
14ran
5unverified

Licence: 4 of the 38 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 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. 1 sample is listed last, in a group without a repository. “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.

harvard-visionlab/lrm-steering community (archive-listed) 13 samples, 10 ran (1 instrument-failed) · 3 unverified
AdaptiveFullstackNorm lrm_models/lrmnet.py ran fingerprinted MIT (permissive) · 126ed34c3a58c622 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
AdaptiveUpsample lrm_models/lrmnet.py ran MIT (permissive) · 8c00bf2ba3f33794 · report fixture: returned AdaptiveUpsample · level recorded 2026-09-22
AddSpatialDimension lrm_models/lrmnet.py ran fingerprinted MIT (permissive) · 8aae4fa13c828688 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
ChannelNorm lrm_models/lrmnet.py ran fingerprinted MIT (permissive) · 753410ece03ec32e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
FeatureExtractor in 24 papers lrm_models/lrmnet.py ran fingerprinted MIT (permissive) · a7f6adc337b5c0ac · report fixture: returned FeatureExtractor · level recorded 2026-09-22
FeedbackScale lrm_models/lrmnet.py ran fingerprinted MIT (permissive) · 3d2b010f98ba752d · report fixture: returned FeedbackScale · level recorded 2026-09-22
MemoryFormatModule lrm_models/lrmnet.py ran MIT (permissive) · 11fbbabed042993e · report fixture: returned MemoryFormatModule · level recorded 2026-09-22
NormSquashResize lrm_models/lrmnet.py ran MIT (permissive) · 5a6abd14dc0a7611 · report fixture: returned NormSquashResize · level recorded 2026-09-22
ResizeNormSquash lrm_models/lrmnet.py ran MIT (permissive) · 67f277bd7c489e7e · report fixture: returned ResizeNormSquash · level recorded 2026-09-22
get_layer_shapes lrm_models/lrmnet.py ran · our draft was wrong MIT (permissive) · c32223f1f7f06e58 · report fixture: signature model:callable/0/?, layer_names:list/1/str, x:Tensor/4/float · returned dict · level recorded 2026-09-22
LongRangeModulation lrm_models/lrmnet.py unverified MIT (permissive) · 863d6ec1313dc270 · report
ModBlock lrm_models/lrmnet.py unverified MIT (permissive) · ad1ef24dc899e552 · report
SteerableLRM lrm_models/lrmnet.py unverified MIT (permissive) · e85d31884a576256 · report
laion-ai/conditioned-prior community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
l2norm in 84 papers
census: 12 implementations from 20 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
util.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 3eb58dae620046d3 · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded, date not recorded
slugify in 12 papers util.py ran fingerprinted MIT (permissive) · 125210403ba29cf0 · report fixture: signature value:str/0/str, allow_unicode:bool/0/bool · returned str · level recorded 2026-09-24
liyinqi/un2clip community (archive-listed) 17 samples, 15 ran (8 instrument-failed) · 2 unverified
Normalize in 154 papers ldm/modules/diffusionmodules/model.py ran · our draft was wrong MIT (permissive) · 9fcdaa6e423e8aa7 · report fixture: signature in_channels:int/0/int, num_groups:int/0/int · returned GroupNorm · level recorded 2026-09-22
append_dims in 30 papers
census: 3 implementations from 6 papers, 1 distinct output on one shared input
ldm/models/diffusion/sampling_util.py ran; the contract check could not run (RAISES) MIT (permissive) · 082e51fd548d78b2 · report fixture: signature x:Tensor/3/float, target_dims:int/0/int · returned Tensor · level recorded 2026-09-24
autocast in 16 papers ldm/util.py ran · our draft was wrong MIT (permissive) · 32af1c12fd826ef2 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-25
clip_fwd eval_mmvpvlm.py ran MIT (permissive) · 2b22d96b91008d68 · report fixture: signature model:callable/0/?, imgs:Tensor/2/float, text1:Tensor/2/float, text2:Tensor/2/float · returned tuple · level recorded 2026-09-24
default in 430 papers ldm/modules/attention.py ran · violated contract MIT (permissive) · 424012cb37b31172 · report fixture: signature val:NoneType/0/?, d:callable/0/? · returned int · level recorded 2026-09-22
disabled_train in 172 papers ldm/models/diffusion/ddpm.py ran · violated contract MIT (permissive) · 4cb732f513d69dfd · report fixture: signature self:callable/0/?, mode:bool/0/bool · returned SimpleModel · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
ldm/modules/attention.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
get_timestep_embedding in 138 papers
census: 11 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
ldm/modules/diffusionmodules/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · cb49209c125de1b4 · report fixture: signature timesteps:Tensor/1/int, embedding_dim:int/0/int · returned Tensor · level recorded, date not recorded
ismap in 70 papers ldm/util.py ran · violated contract fingerprinted MIT (permissive) · d72762b700feee6f · report fixture: signature x:Tensor/4/float · returned bool · level recorded 2026-09-24
nonlinearity in 140 papers
census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
ldm/modules/diffusionmodules/model.py ran · our draft was wrong fingerprinted MIT (permissive) · 3137073275f8c21a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
norm_thresholding in 12 papers ldm/models/diffusion/sampling_util.py ran fingerprinted MIT (permissive) · 9898fe8b041f354c · report fixture: signature x0:Tensor/2/float, value:float/0/float · returned Tensor · level recorded 2026-09-24
openclip_fwd eval_mmvpvlm.py ran MIT (permissive) · 1aafd47605e9ff11 · report fixture: signature model:callable/0/?, imgs:Tensor/2/float, text1:Tensor/2/float, text2:Tensor/2/float · returned tuple · level recorded 2026-09-24
spatial_norm_thresholding in 10 papers ldm/models/diffusion/sampling_util.py ran · our draft was wrong fingerprinted MIT (permissive) · d86694c13b94ae3a · report fixture: signature x0:Tensor/2/float, value:float/0/float · returned Tensor · level recorded 2026-09-24
uniform_on_device in 45 papers ldm/models/diffusion/ddpm.py ran · our draft was wrong MIT (permissive) · d48d8354986e3b0e · report fixture: signature r1:float/0/float, r2:float/0/float, shape:tuple/1/int, device:device/0/? · returned Tensor · level recorded, date not recorded
uniq in 117 papers ldm/modules/attention.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 9a299fe5ae09e407 · report fixture: signature arr:list/1/int · returned dict_keys · level recorded 2026-09-22
benchmark_model eval_mmvpvlm.py unverified MIT (permissive) · 730edc91bdf40519 · report
log_txt_as_img in 72 papers ldm/util.py unverified MIT (permissive) · f9bd2e83191afad1 · report
lucidrains/DALLE2-pytorch community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
NoiseScheduler dalle2_pytorch/dalle2_pytorch.py ran · metamorphic tier: deterministic MIT (permissive) · 78cd7549fb76becd · report fixture: returned NoiseScheduler · level recorded 2026-09-22
cosine_beta_schedule in 76 papers dalle2_pytorch/dalle2_pytorch.py ran · honoured contract fingerprinted MIT (permissive) · 63d04624697c8f60 · report fixture: signature timesteps:int/0/int, s:float/0/float · returned Tensor · level recorded 2026-09-22
first in 17 papers dalle2_pytorch/dalle2_pytorch.py ran · violated contract MIT (permissive) · 3072294c9b32cf4b · report fixture: signature arr:list/1/int, d:NoneType/0/? · returned int · level recorded 2026-09-22
quadratic_beta_schedule in 9 papers dalle2_pytorch/dalle2_pytorch.py ran · honoured contract fingerprinted MIT (permissive) · 7bc0ce30656f4c4a · report fixture: signature timesteps:int/0/int · returned Tensor · level recorded 2026-09-22
sigmoid_beta_schedule in 5 papers dalle2_pytorch/dalle2_pytorch.py ran · honoured contract fingerprinted MIT (permissive) · 48e7ff5be83206c0 · report fixture: signature timesteps:int/0/int · returned Tensor · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
default in 430 papers repository not located ran · violated contract licence of this copy not recorded · 915fbeb88e13d4a3 · report fixture: signature val:str/0/str, d:callable/0/? · returned str · level recorded 2026-09-22

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.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Hierarchical Text-Conditional Image Generation with CLIP Latents (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Hierarchical Text-Conditional Image Generation with CLIP Latents (graph method: Hierarchical Text-Conditional Image Generation with CLIP Latents). 9 bricks; individually on a fixture: 8 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 3 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. NoiseScheduler entry · level 1 · ran · 78cd7549fb76becd
  2. cosine_beta_schedule scheduler · level 1 · ran · honoured contract · 63d04624697c8f60
  3. default helper · level 1 · ran · violated contract · 915fbeb88e13d4a3
  4. extract helper · level 0 · unverified · 09c8479d9a5b3e06
  5. linear_beta_schedule scheduler · level 1 · ran · honoured contract · 482723f534770483
  6. quadratic_beta_schedule scheduler · level 1 · ran · honoured contract · 7bc0ce30656f4c4a
  7. sigmoid_beta_schedule scheduler · level 1 · ran · honoured contract · 48e7ff5be83206c0
  8. first helper · level 1 · ran · violated contract · 3072294c9b32cf4b
  9. exists helper · level 1 · ran · violated contract · aa5486a3650902d8

harvested Assembly for Hierarchical Text-Conditional Image Generation with CLIP Latents (graph method: Hierarchical Text-Conditional Image Generation with CLIP Latents). 13 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. SteerableLRM entry · level 0 · unverified · e85d31884a576256
  2. LongRangeModulation model · level 0 · unverified · 863d6ec1313dc270
  3. ModBlock model · level 0 · unverified · ad1ef24dc899e552
  4. get_layer_shapes helper · level 1 · ran · our draft was wrong · c32223f1f7f06e58
  5. MemoryFormatModule helper · level 1 · ran · 11fbbabed042993e
  6. NormSquashResize helper · level 1 · ran · 5a6abd14dc0a7611
  7. ResizeNormSquash helper · level 1 · ran · 67f277bd7c489e7e
  8. FeatureExtractor helper · level 1 · ran · a7f6adc337b5c0ac
  9. AdaptiveFullstackNorm helper · level 1 · ran · 126ed34c3a58c622
  10. AdaptiveUpsample helper · level 1 · ran · 8c00bf2ba3f33794
  11. AddSpatialDimension helper · level 1 · ran · 8aae4fa13c828688
  12. ChannelNorm helper · level 1 · ran · 753410ece03ec32e
  13. FeedbackScale model · level 1 · ran · 3d2b010f98ba752d

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="2204.06125") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Conditional Image GenerationDecoderDiversityImage GenerationText-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) DALL-E 2 FID 10.39 #26 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: DALL·E 2

CLIPDALL·E 2Diffusion

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