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 ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2204.06125")

Code

Syntology Ran 29 of 38 code samples harvested from 4 repositories linked to this paper; 9 have no recorded run. Of those that ran: 3 ran · honoured contract; 5 ran · violated contract; 6 ran · our draft was wrong; 1 ran · fixture could not drive it; 14 ran with no contract checked.

By repository: community (archive-listed): 37 samples from 4 repositories, 28 ran; 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.

drboog/Shifted_Diffusion mentioned on GitHubjaxCC0-1.0 report
facebookresearch/multimodal mentioned on GitHubpytorch report
harvard-visionlab/lrm-steering mentioned on GitHubpytorch report
kakaobrain/coyo-dataset mentioned on GitHubpytorch report
laion-ai/conditioned-prior mentioned on GitHubpytorchMIT report
liyinqi/un2clip mentioned on GitHubpytorchMIT report
woctezuma/steam-CLIP mentioned on GitHubMIT 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

38 samples harvested; 29 ran; 3 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · honoured contract
5ran · violated contract
6ran · our draft was wrong
1ran · fixture could not drive it
14ran
9unverified

Licence: 1 of the 38 samples is 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 4 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

AdaptiveFullstackNorm harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran fingerprinted MIT (permissive) · 126ed34c3a58c622 · report
AdaptiveUpsample harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran MIT (permissive) · 8c00bf2ba3f33794 · report
AddSpatialDimension harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran fingerprinted MIT (permissive) · 8aae4fa13c828688 · report
ChannelNorm harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran fingerprinted MIT (permissive) · 753410ece03ec32e · report
FeatureExtractor harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran fingerprinted MIT (permissive) · a7f6adc337b5c0ac · report
FeedbackScale harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran fingerprinted MIT (permissive) · 3d2b010f98ba752d · report
MemoryFormatModule harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran MIT (permissive) · 11fbbabed042993e · report
NoiseScheduler lucidrains/DALLE2-pytorch/dalle2_pytorch/dalle2_pytorch.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 78cd7549fb76becd · report
NormSquashResize harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran MIT (permissive) · 5a6abd14dc0a7611 · report
Normalize liyinqi/un2clip/ldm/modules/diffusionmodules/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9fcdaa6e423e8aa7 · report
ResizeNormSquash harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran MIT (permissive) · 67f277bd7c489e7e · report
append_dims liyinqi/un2clip/ldm/models/diffusion/sampling_util.py community (archive-listed) ran MIT (permissive) · 082e51fd548d78b2 · report
cosine_beta_schedule lucidrains/DALLE2-pytorch/dalle2_pytorch/dalle2_pytorch.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 63d04624697c8f60 · report
default liyinqi/un2clip/ldm/modules/attention.py community (archive-listed) ran · violated contract MIT (permissive) · 424012cb37b31172 · report
disabled_train liyinqi/un2clip/ldm/models/diffusion/ddpm.py community (archive-listed) ran · violated contract MIT (permissive) · 4cb732f513d69dfd · report
exists liyinqi/un2clip/ldm/modules/attention.py community (archive-listed) ran · violated contract MIT (permissive) · aa5486a3650902d8 · report
first lucidrains/DALLE2-pytorch/dalle2_pytorch/dalle2_pytorch.py community (archive-listed) ran · violated contract MIT (permissive) · 3072294c9b32cf4b · report
get_layer_shapes harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · c32223f1f7f06e58 · report
get_timestep_embedding liyinqi/un2clip/ldm/modules/diffusionmodules/model.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · cb49209c125de1b4 · report
ismap liyinqi/un2clip/ldm/util.py community (archive-listed) ran MIT (permissive) · d72762b700feee6f · report
l2norm laion-ai/conditioned-prior/util.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 3eb58dae620046d3 · report
nonlinearity liyinqi/un2clip/ldm/modules/diffusionmodules/model.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 3137073275f8c21a · report
norm_thresholding liyinqi/un2clip/ldm/models/diffusion/sampling_util.py community (archive-listed) ran fingerprinted MIT (permissive) · 9898fe8b041f354c · report
quadratic_beta_schedule lucidrains/DALLE2-pytorch/dalle2_pytorch/dalle2_pytorch.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 7bc0ce30656f4c4a · report
sigmoid_beta_schedule lucidrains/DALLE2-pytorch/dalle2_pytorch/dalle2_pytorch.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 48e7ff5be83206c0 · report
spatial_norm_thresholding liyinqi/un2clip/ldm/models/diffusion/sampling_util.py community (archive-listed) ran fingerprinted MIT (permissive) · d86694c13b94ae3a · report
uniform_on_device liyinqi/un2clip/ldm/models/diffusion/ddpm.py community (archive-listed) ran · our draft was wrong MIT (permissive) · d48d8354986e3b0e · report
uniq liyinqi/un2clip/ldm/modules/attention.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 9a299fe5ae09e407 · report
LongRangeModulation harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) unverified MIT (permissive) · 863d6ec1313dc270 · report
ModBlock harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) unverified MIT (permissive) · ad1ef24dc899e552 · report
SteerableLRM harvard-visionlab/lrm-steering/lrm_models/lrmnet.py community (archive-listed) unverified MIT (permissive) · e85d31884a576256 · report
autocast liyinqi/un2clip/ldm/util.py community (archive-listed) unverified MIT (permissive) · 32af1c12fd826ef2 · report
benchmark_model liyinqi/un2clip/eval_mmvpvlm.py community (archive-listed) unverified MIT (permissive) · 730edc91bdf40519 · report
clip_fwd liyinqi/un2clip/eval_mmvpvlm.py community (archive-listed) unverified MIT (permissive) · 2b22d96b91008d68 · report
log_txt_as_img liyinqi/un2clip/ldm/util.py community (archive-listed) unverified MIT (permissive) · f9bd2e83191afad1 · report
openclip_fwd liyinqi/un2clip/eval_mmvpvlm.py community (archive-listed) unverified MIT (permissive) · 1aafd47605e9ff11 · report
slugify laion-ai/conditioned-prior/util.py community (archive-listed) unverified MIT (permissive) · 125210403ba29cf0 · report
default identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · 915fbeb88e13d4a3 · report

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