SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.11487 · NeurIPS · 2022

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

Tim Salimans, Mohammad Norouzi, David Fleet, Lala Li, Jonathan Ho, Emily Denton, William Chan, Burcu Karagol, Saurabh Saxena, Seyed Kamyar, Seyed Ghasemipour, Jay Whang, and 3 more

arXiv · PDF · Open in the Atlas

Code that ran

5 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2205.11487.json · badge: /api/ran/2205.11487.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
deep-floyd/if community
Papers with Code archive
4 ran · 4 no recorded run
teapearce/conditional_diffusion_mnist community
Papers with Code archive
1 ran · 1 no recorded run
cene555/Imagen-pytorch community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
AttentionPooling Ran
ran on a synthesized input · constructed an object; no result was computed
deep-floyd/if/deepfloyd_if/model/unet.py
pointer only (licence: NOASSERTION) · get_code("572c310ea05bf309")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, deep-floyd/if (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Downsample Ran
ran on a synthesized input · constructed an object; no result was computed
deep-floyd/if/deepfloyd_if/model/unet.py
pointer only (licence: NOASSERTION) · get_code("93058e5e24fa4d4a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, deep-floyd/if (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

QKVAttention Ran
ran on a synthesized input · constructed an object; no result was computed
deep-floyd/if/deepfloyd_if/model/unet.py
pointer only (licence: NOASSERTION) · get_code("c024083e30c5368d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, deep-floyd/if (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

UnetDown Ran
ran on a synthesized input
teapearce/conditional_diffusion_mnist/script.py
code served (permissive licence) · get_code("c1a53d10c7cfa17e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

class ResidualConvBlock(nn.Module):

    def __init__(self, in_channels: int, out_channels: int, is_res: bool=False) -> None:
        super().__init__()
        '\n        standard ResNet style convolutional block\n        '
        self.same_channels = in_channels == out_channels
        self.is_res = is_res
        self.conv1 = nn.Sequential(nn.Conv2d(in_channels, out_channels, 3, 1, 1), nn.BatchNorm2d(out_channels), nn.GELU())
        self.conv2 = nn.Sequential(nn.Conv2d(out_channels, out_channels, 3, 1, 1), nn.BatchNorm2d(out_channels), nn.GELU())

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        if self.is_res:
            x1 = self.conv1(x)
            x2 = self.conv2(x1)
            if self.same_channels:
                out = x + x2
            else:
                out = x1 + x2
            return out / 1.414
        else:
            x1 = self.conv1(x)
            x2 = self.conv2(x1)
            return x2

class UnetDown(nn.Module):

    def __init__(self, in_channels, out_channels):
        super(UnetDown, self).__init__()
        '\n        process and downscale the image feature maps\n        '
        layers = [ResidualConvBlock(in_channels, out_channels), nn.MaxPool2d(2)]
        self.model = nn.Sequential(*layers)

    def forward(self, x):
        return self.model(x)


INIT_ARGS = {
    'in_channels': 3,
    'out_channels': 4,
}

ARGS = {
    'x': torch.randn(2, 3, 8, 8),
}

if __name__ == '__main__':
    model = UnetDown(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Input shape: {ARGS['x'].shape}")
    print(f"Output shape: {output.shape}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 4, 4) — shape (2, 4, 4, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Upsample Ran
ran on a synthesized input · constructed an object; no result was computed
deep-floyd/if/deepfloyd_if/model/unet.py
pointer only (licence: NOASSERTION) · get_code("4f1ccffbc59c4bbe")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, deep-floyd/if (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

AttentionBlock Not yet run
unverified (harvested, no recorded run)
deep-floyd/if/deepfloyd_if/model/unet.py
pointer only (licence: NOASSERTION) · get_code("83356f082da409f5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, deep-floyd/if (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

ContextUnet Not yet run
unverified (harvested, no recorded run)
teapearce/conditional_diffusion_mnist/script.py
code served (permissive licence) · get_code("156e412579f74583")
How it ran

no invocation recorded.

ResBlock Not yet run
unverified (harvested, no recorded run)
deep-floyd/if/deepfloyd_if/model/unet.py
pointer only (licence: NOASSERTION) · get_code("9878524ba095b65b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, deep-floyd/if (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Text2ImUNet Not yet run
unverified (harvested, no recorded run)
cene555/Imagen-pytorch/imagen_pytorch/text2im_model.py
pointer only (licence: NONE) · get_code("7fcd4eb74a12867c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, cene555/Imagen-pytorch when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

TimestepEmbedSequential Not yet run
unverified (harvested, no recorded run)
deep-floyd/if/deepfloyd_if/model/unet.py
pointer only (licence: NOASSERTION) · get_code("79ba2446de89789e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, deep-floyd/if (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

UNetModel Not yet run
unverified (harvested, no recorded run)
deep-floyd/if/deepfloyd_if/model/unet.py
pointer only (licence: NOASSERTION) · get_code("c27dfab7177fdf2b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, deep-floyd/if (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
TimestepEmbedSequential
brick of this paper's assembly: helper, model
4 other papers
2 dated earlier, 2 later
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2112.10741 (2021-12)
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
2310.03502 (2023-10)
Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion
and 1 more not named here
AttentionBlock
brick of this paper's assembly: model
1 other paper
1 later
2601.00328 (2026-01)
Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion
QKVAttention
brick of this paper's assembly: model
1 other paper
1 later
2601.00328 (2026-01)
Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion
ResBlock
brick of this paper's assembly: model
1 other paper
1 later
2601.00328 (2026-01)
Joint Geometry-Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 imagetext 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, GLIDE and DALL-E 2, and find that human raters prefer Imagen over other models in side-byside comparisons, both in terms of sample quality and image-text alignment. See imagen.research.google for an overview of the results. * Equal contribution. † Core contribution.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2205.11487")
get_code_for_paper("2205.11487")
have("2205.11487")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2205.11487.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2205.11487.svg)](https://syntology.ai/paper/2205.11487)

Connect an agent — have() is free.