Repositorium für die Medienwissenschaft

Eryk Salvaggio
How to Read an AI Image: Toward a Media Studies
Methodology for the Analysis of Synthetic Images
2023
https://doi.org/10.25969/mediarep/22328

Veröffentlichungsversion / published version

Zeitschriftenartikel / journal article

Empfohlene Zitierung / Suggested Citation:

Salvaggio, Eryk: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images.
In: IMAGE. Zeitschrift für interdisziplinäre Bildwissenschaft. Generative Imagery: Towards a ‘New Paradigm’ of Machine
Learning-Based Image Production, Jg. 19 (2023), Nr. 1, S. 83–99. DOI: https://doi.org/10.25969/mediarep/22328.

Nutzungsbedingungen: Terms of use:

Dieser Text wird unter einer Deposit-Lizenz (Keine This document is made available under a Deposit License (No
Weiterverbreitung - keine Bearbeitung) zur Verfügung gestellt. Redistribution - no modifications). We grant a non-exclusive,
Gewährt wird ein nicht exklusives, nicht übertragbares, non-transferable, individual, and limited right for using this
persönliches und beschränktes Recht auf Nutzung dieses document. This document is solely intended for your personal,
Dokuments. Dieses Dokument ist ausschließlich für non-commercial use. All copies of this documents must retain
den persönlichen, nicht-kommerziellen Gebrauch bestimmt. all copyright information and other information regarding legal
Auf sämtlichen Kopien dieses Dokuments müssen alle protection. You are not allowed to alter this document in any
Urheberrechtshinweise und sonstigen Hinweise auf gesetzlichen way, to copy it for public or commercial purposes, to exhibit the
Schutz beibehalten werden. Sie dürfen dieses Dokument document in public, to perform, distribute, or otherwise use the
nicht in irgendeiner Weise abändern, noch dürfen Sie document in public.
dieses Dokument für öffentliche oder kommerzielle Zwecke By using this particular document, you accept the conditions of
vervielfältigen, öffentlich ausstellen, aufführen, vertreiben oder use stated above.
anderweitig nutzen.
Mit der Verwendung dieses Dokuments erkennen Sie die
Nutzungsbedingungen an.
IMAGE HERBERT VON HALEM VERLAG
The Interdisciplinary Journal of Image Sciences
37(1), 2023, S. 83-99
ISSN 1614-0885
DOI: 10.1453/1614-0885-1-2023-15456

Eryk Salvaggio

How to Read an AI Image: Toward a Media

Studies Methodology for the Analysis of
Synthetic Images

Abstract: Image-generating approaches in machine learning, such as GANs and

Diffusion, are actually not generative but predictive. AI images are data patterns
inscribed into pictures, and they reveal aspects of these image-text datasets and
the human decisions behind them. Examining AI-generated images as ‘info-
graphics’ informs a methodology, as described in this paper, for the analysis of
these images within a media studies framework of discourse analysis. This paper
proposes a methodological framework for analyzing the content of these images,
applying tools from media theory to machine learning. Using two case studies,
the paper applies an analytical methodology to determine how information
patterns manifest through visual representations. This methodology consists of
generating a series of images of interest, following Roland Barthes’ advice that
“what is noted is by definition notable” (Barthes 1977: 89). It then examines
this sample of images as a non-linear sequence. The paper offers examples of
certain patterns, gaps, absences, strengths, and weaknesses and what they might
suggest about the underlying dataset. The methodology considers two frames of
intervention for explaining these gaps and distortions: Either the model imposes
a restriction (content policies), or else the training data has included or excluded
certain images, through conscious or unconscious bias. The hypothesis is then
extended to a more randomized sample of images. The method is illustrated by
two examples. First, it is applied to images of faces produced by the StyleGAN2
model. Second, it is applied to images of humans kissing created with DALL·E 2.
This allows us to compare GAN and Diffusion models, and to test whether the
method might be generalizable. The paper draws some conclusions to the
hypotheses generated by the method and presents a final comparison to an actu-
al training dataset for StyleGAN2, finding that the hypotheses were accurate.

IMAGE | 37(1), 2023 83

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

Background

Every AI-generated image is an infographic about the underlying dataset. AI imag-

es are data patterns inscribed into pictures, and they tell us stories about these
image-text datasets and the human decisions behind them. As a result, AI images
can become readable as ‘texts’. The field of media studies has acknowledged
“culture depends on its participants interpreting meaningfully what is around
them […] in broadly similar ways” (Hall 1997: 2). Images draw their power from
intentional assemblages of choices, steered toward the purpose of communica-
tion. Roland Barthes suggests that images draw from and produce myths, a “col-
lective representation” which turns “the social, the cultural, the ideological, and
the historical into the natural” (Barthes 1977: 165). Such myths are encoded into
images by their creators and decoded by consumers (cf. Hall 1992: 117). For the
most part, these assumptions have operated on the presumption that humans,
not machines, were the ones encoding these meanings into images.
An AI has no unconscious mind, but nonetheless, contemporary Diffu-
sion-based models produce images trained from collections of image-text pair-
ings – datasets – which are produced and assembled by humans. The images
in these datasets exemplify these collective myths and unstated assumptions.
Rather than being encoded into the unconscious minds of the viewer or artist,
they are inscribed into datasets. Machine learning models are meant to identify
patterns in these datasets among vast numbers of images: DALL·E 2, for instance,
was trained on 250 million text and image pairings (cf. Ramesh et al. 2021: 4).
These datasets, like the images they contain, are created within specific cultural,
political, social, and economic contexts. Machines are programmed in ways that
inscribe and communicate the unconscious assumptions of human data-gather-
ers, who embed these assumptions into human-assembled datasets.
This paper proposes that when datasets are encoded into new sets of imag-
es, these generated images reveal layers of cultural and social encoding within
the data used to produce them. This line of reasoning leads us to the research
question: How might we read human myths through machine-generated imag-
es? In other words, what methods might we use to interrogate these images for
cultural, social, political, or other artifacts? In the following, I will describe a
loose methodology based on my training in media analysis at the London School
of Economics, drawing from semiotic visual analysis. This approach is meant
to “produce detailed accounts of the exact ways the meanings of an image are
produced through that image” (Rose 2012: 106). Rather than interpreting the
images as one might an advertisement or film still, I suggest that AI images are
best understood as infographics for their underlying dataset. The infographic, a
fusion of information and graphics, has elsewhere been defined as the “visual rep-
resentations of data, information, or concepts” (Chandler/Munday 2011: 208)

IMAGE | 37(1), 2023 84

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

that “consolidate and display information graphically in an organized way so

a viewer can readily retrieve the information and make specific and/or overall
observations from it” (Harris 1999: 198). The ‘infographics’ proposed here lack
keys for interpreting the information they present because they are not designed
to be interpreted as data but as imagery intended for human observers. Instead,
we must use a semiotic analysis to reverse engineer the data-driven decisions that
produced the image.

Conceptual Framework

The present paper proposes a methodology to understand, interpret, and critique

the ‘inhuman’ outputs of generative imagery through a basic visual semiotic
analysis as outlined in an introductory text by Gillian Rose (2001). It is intended
to offer a similar introductory degree of simplicity. I began this work as an art-
ist working with GANs in 2019, creating datasets – as well as images from these
datasets. Through this work, I noticed patterns in the output, where information
that was underrepresented in the dataset would be weakly defined in the corre-
sponding images. Using StyleGAN to create diverse images of faces consistently
produced more white faces than black ones. When black faces were generated,
they lacked the definition of features found in white faces. This was particular-
ly true for black women. In aiming to understand this phenomenon, I drew on
media analysis techniques combined with an education in Applied Cybernetics,
which examines complex systems through relationships and exchanges between
components and their resulting feedback loops. While the present case studies
examine the faces of black women in StyleGAN and images of men and women
kissing in DALL·E 2, reflecting also on (the absence of) queer representations, the
author is white and heterosexual. Any attempted determination of race, sexuali-
ty, or gender in AI-generated images inherently reflects this subjectivity.

Technical Background

Every image produced by diffusion models like DALL·E 2, Stable Diffusion, or

Midjourney begins as a random image of Gaussian noise. When we prompt a
Diffusion model to create an image, it takes this static and tries to reduce it.
After a series of steps, it may arrive at a picture that matches the text descrip-
tion of one’s prompt. The prompt is understood as a caption, and the algorithm
works to ‘find’ the image in random noise based on this caption. Consider the
way we look for constellations in the nighttime sky: If I tell you a constellation
is up there, you mind find it – even if it isn’t. Diffusion models are designed to

IMAGE | 37(1), 2023 85

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

find constellations among ever-changing stars. Diffusion models are trained

by watching images decay. Every image in the data has its information removed
over a sequence of steps. This introduces noise, and the model is designed to trace
the dispersal of this noise (or diffusion, hence the name) across the image. The
noise follows a Gaussian distribution pattern, and as the images break down,
noise clusters in areas where similar pixels are clustered. In human terms, this
is like raindrops scattering an ink drawing across a page. Based on what remains
of the image, the trajectory of droplets and motion of the ink, we may be able to
infer where the droplet landed and what the image represented before the splash.
A Diffusion model is designed to sample the images, with their small differ-
ences in clusters of noise, and compare them. In doing this, the model makes a
map of how the noise came in: learning how the ink smeared. It calculates the
change between one image and the next, like a trail of breadcrumbs that lead
back to the previous image. It will measure what changed between the clear
image and the slightly noisier image. If we examine images in the process, we
will see clusters of pixels around denser concentrations of the image. For exam-
ple, flower petals, with their bright colors, stay visible after multiple generations
of noise have been introduced. Gaussian noise follows a loose pattern, but one
that tends to cluster around a central space. This digital residue of the image is
enough to suggest a possible starting point for generating a similar image. From
that remainder, it can find correlations in the pathways back to similar images.
The machine is accounting for this distribution of noise and calculating a way to
reverse it.
Once complete, information about the way this image breaks apart enters
into a larger abstraction, which is categorized by association. This association is
learned through the text-image pairings of CLIP (DALL·E 2) or LAION (Stable Diffu-
sion, Midjourney, and others). The category flowers, for example, contains infor-
mation about the breakdown of millions of images with the caption “flowers”.
As a result, the model can work its way backward from noise, and if given this
prompt, “flowers”, it can arrive at some generalized representation of a flower
common to these patterns of clustering noise. That is to say: it can produce a per-
fect stereotype of a flower, a representation of any central tendencies found with-
in the patterns of decay. When the model encounters a new, randomized frame
of static, it applies those stereotypes in reverse, seeking these central tendencies
anew, guided by the prompt. It will follow the path drawn from the digital resi-
due of these flower images. Each image has broken down in its own way, but they
share patterns of breakdown: clusters of noise around the densest concentrations
of pixels, representing the strongest signal within the original images. In figure 1,
we see an image of flowers compared to the ‘residue’ left behind as it is broken
down.

IMAGE | 37(1), 2023 86

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

Figure 1: As Gaussian noise is introduced to the image, clusters remain around the
densest concentrations of pixel information; created with Stable Diffusion in February
2023

As the model works backward from noise, our prompts constrain the possible
pathways that the model is allowed to take. Prompted with “flowers”, the model
cannot use what it has learned about the breakdown of cat photographs. We
might constrain it further: “Flowers in the nighttime sky”. This introduces new
sets of constraints: “Flowers”, but also “night”, and “sky”. All of these words are
the result of datasets of image-caption pairs taken from the world wide web. CLIP
and LAION aggregate this information and then ignore the inputs. These images,
labeled by internet users, are assembled into categories, or categories are inferred
by the model based on its similarities to existing categories. All that remains
is data – itself a biased and constrained representation of the social consensus,
shaped by often arbitrary, often malicious, and almost always unconsidered
boundaries about what defines these categories.
This paper proposes that when we look at AI images, specifically Diffusion
images, we are looking at infographics about these datasets, including their
categories, biases, and stereotypes. To read these images, we consider them rep-
resentations of the underlying data, visualizing an ‘internet consensus’. They
produce images where prompts produce abstractions of centralizing tendencies.
When images are more closely aligned to the abstract ideal of these stereotypes,
they are clean, ‘strong’ images. When images drift from this centralizing con-
sensus, they are more difficult to categorize. Therefore, images of certain catego-
ries may appear ‘weak’ – either occurring less often or with lower definition or
clarity.
These ideal ‘types’ are socially constructed and encoded by anyone who
uploads an image to the internet with a descriptive caption. For example, a ran-
dom sample of the training data associated with the phrase “Typical American”
within the LAION 5B dataset that drives Stable Diffusion suggests the images and
associations for “Typical American” as a category: images of flags, painted faces
from Independence Day events, as would be expected. Social stereotypes, related

IMAGE | 37(1), 2023 87

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

to obesity and cowboy hats, are also prevalent. Curiously, one meme appears
multiple times, a man holding a Big Gulp from 7-11 (a kind of large, frozen sugar
drink). Figure 2 is an image in response to the prompt “Typical American” in
which the man holds a large beverage container, like a Big Gulp, whilst wearing
face paint and a cowboy hat. We see that while the relationship between the data-
set and the images that Diffusion produces are not literal, these outcomes are
nonetheless connected to the concepts tied to this phrase within the dataset.

Figure 2: A result from the prompt “Typical

American” from Stable Diffusion in February
2023

Just as archives are the stories of those who curate them, Diffusion generated
images are no different. They visualize the constraints of the prompt, as defined
by a dataset of human-generated captions that is assembled by CLIP or LAION’s
automated categorizations. I propose that these images are a visualization of this
archive. They struggle to show anything the archive does not contain or is not
clearly categorized in accordance with prompts. This suggests that we can read
images created by these systems. The next section proposes a methodology for
reading these images which blends media analysis and data auditing techniques.
As a case study, it presents DALL·E 2 generated images of people kissing.

Methodology

Here I will briefly outline the methodology, followed by an explanation of each

step in greater detail.
1. Produce images until you find one image of particular interest.
2. Describe the image simply, making note of interesting and uninteresting
features.
3. Create a new set of samples, drawing from the same prompt or dataset.

IMAGE | 37(1), 2023 88

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

4. Conduct a content analysis of these sample images to identify strengths and

weaknesses.
5. Connect these patterns to corresponding strengths and weaknesses in the
underlying dataset.
6. Re-examine the original image of interest.
Each step is explained through a case study of an image produced through
DALL·E 2. The prompt used to generate the image was “Photograph of two
humans kissing”. This prompt was used until an image of particular interest
caught my eye. Each step is described, with further discussions of the step inte-
grated into each section.

Figure 3: “Photograph of two humans

kissing”, produced with DALL·E 2 in February
2023

1. Produce Images until you Find one of Particular Interest

First, we require a research question. There is no methodology for selecting

images of interest. Following Rose, images were chosen subjectively, “on the
basis of how conceptually interesting they are” (Rose 2012: 73). Images must be
striking, but their relevance is best determined by the underlying question being
pursued by the researcher. The case studies offered here were produced through
simple curiosity. I aimed to see if a sophisticated AI models could create compel-
ling images of human emotion. I began with the image displayed in figure 3.

IMAGE | 37(1), 2023 89

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

2. Describe the Image Simply, Making Note of Interesting and

Uninteresting Features

We need to know what is in the image in order to assess why they are there. In
Case Study 1 (fig. 3), the image portrays a heterosexual white couple. A reluc-
tant (?) male is being kissed by a woman. In this case, the man’s lips are protrud-
ing, which is rare compared to our sample. The man is also weakly represented:
his eyes and ears have notable distortions. In the following analysis of the image,
weak features thus refer to smudged, blurry, distorted, glitched, or otherwise
striking features of the image. Strong features represent aspects of the image that
are of high clarity, realistic, or at least realistically represented.
While this paper examines photographs, similar weak and strong presence
can be found in a variety of images produced through Diffusion systems in other
styles as well. For example, if oil paintings frequently depict houses, trees, or a
particular style of dress, it may be read as a strong feature that would be matched
to a strong correspondence with aspects of the dataset. You may discover that
producing oil paintings in the style of 18th century European masters does not
generate images of black women. This would be a weak signal from the data, sug-
gesting that the referenced datasets of 18th century portraiture did not contain
portraits of black women (Note that these are hypotheticals and have not been
specifically verified).

3. Create a New Set of Samples, Drawing from the Same Prompt

or Database

Creating a wider variety of samples allows us to identify patterns that might

reveal this central tendency in the abstraction of the image model. As the model
works backwards from noise – following constraints on what it can find in that
noise – we want to create many images to identify any gravitation toward its
average representation. It is initially challenging to find insights into a dataset
through a single image. However, generative images are a medium of scale: mil-
lions of images can be produced in a day, with streaks of variations and anom-
alies. None of these reflect a single author’s choices. Instead, they blend thou-
sands, even millions of aggregated choices. By examining the shared properties
of many images produced by the same prompt or dataset, we can begin to under-
stand the underlying properties of the data that formed them. In this sense, AI
imagery may be analyzed as a series of film stills: a sequence of images, oriented
toward ‘telling the same story’. That story is the dataset. The dataset is revealed
through a non-linear sequence, and a larger sample will consist of a series of
images designed to tell that same story. Therefore, we would create variations

IMAGE | 37(1), 2023 90

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

using the same prompt or model. I use a minimum of nine, because nine images
can be placed side by side and compared on a grid. For some examinations, I have
generated 18-27 or as many as 90-120. While creating this expanded sample set,
we would continue to look for any conceptually interesting images from the same
prompt. These images do not have to be notable in the same way that the initial
source image was. The image that fascinated, intrigued, or irritated us was inter-
esting for a reason. The priority is to understand that reason by understanding
the context – interpreting the patterns present across many similarly generat-
ed images. We will not yet have a coherent theory of what makes these images
notable. We are simply trying to understand the generative space that surrounds the
image of interest. This generative, or latent space, is where the data’s weaknesses
and strengths present themselves. Even a few samples will produce recognizable
patterns, after all.

Figure 4: Nine images created from the

same prompt as our source image, created
with DALL·E 2 in February 2023. If you want to
generate your own, you can type “Photograph
of humans kissing” into DALL·E 2 and grab
samples for comparison yourself

4. Conduct a Content Analysis of these Sample Images to Identify

Individual Strengths and Weaknesses

Now we can study the new set of images for patterns and similarities by applying
a form of content analysis. We describe what the image portrays ‘literally’ (the
denoted meaning). Are there particularly strong correlations between any of the
images? Look for certain compositions/arrangements, color schemes, lighting
effects, figures or poses, or other expressive elements, that are strong across all
(or some meaningful subsections) of the sample pool. These indicate certain
biases in the source data. When patterns are present, we will call these signals.
Akin to symptoms, indicators are observable elements of the image that point to
a common underlining cause. We may have strong signals: suggesting frequency

IMAGE | 37(1), 2023 91

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

of the pattern in the data pattern, the strongest signals being near-universal and
the strongest dismissed as obvious. A strong signal would include tennis balls
being round, cats having fur, etc. A weak signal, on the other hand, suggests that
the image is on the peripheral of the model’s central tendencies for the prompt.
The most obvious indicators of weak signals are images that simply cannot be
created realistically or with great detail. The smaller the number of examples in
a dataset, the fewer images the model may learn from, and the more errors will
be present in whatever it generates. These may be visible in blurred appearances,
such as smudges, glitches, or distortions. Weak signals may also be indicated
through a comparison of what patterns are present against what patterns might
otherwise be possible.
Strong signals: In the given example, the images render skin textures quite
well. They seem professionally lit, with studio backgrounds. They are all close-
ups focused on the couple. Women tend to have protruding lips, while men tend
to have their mouths closed. These therefore suggest strong signals in the data,
suggesting an adjacency to central tendencies within the assigned category of
the prompt. These signals may not be consistent across all images, but are impor-
tant to recognize because they provide a contrast and context for what is weakly
represented.
Weak signals: In the case study, two important things are apparent to me. First,
most pictures are heteronormative, i.e., the images portray only man/woman
couples. The present test run, created in November 2022, differs from an earlier
test set (created in October 2022 and made public online, cf. Salvaggio 2022).
In the original test set, all couples were heterosexual. Second, there is a strong
presence of multiracial couples: another change from October 2022 when nearly
all couples shared skin tones. Third, they are missing convincing interpersonal
contact. This is, in fact, identical in both datasets from different months. The
strong signal across the kissing images might be a sense of hesitancy as if an invis-
ible barrier exists between the two partners in the image. The lips of the figures
are weak: inconsistent and imperfect. With an inventory of strong and weak pat-
terns, we can begin asking critical questions toward a hypothesis.
1. What data would need to be present to explain these strong signals?
2. What data would need to be absent to explain these weak signals?
Weaknesses in your images may be a result of sparse training data, training
biased toward exclusion, or reductive system interventions such as censorship.
Strengths may be the result of prevalence in your training data, or encouraged
by system interventions. They may also represent cohesion between your prompt
and the ‘central tendency’ of images in the dataset, for example, if you prompt
“apple”, you may produce more consistent and realistic representations of apples
than if you request an “apple-car”. For example, DALL·E 2 introduces diversifying
keywords randomly into prompts (cf. Offert/Phan 2022). The more often some

IMAGE | 37(1), 2023 92

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

feature is in the data, the more often it will be emphasized in the image. In sum-
mary, you can only see what’s in the data and you cannot see what is not in the
data. When something is strikingly wrong or unconvincing, or repeatedly impos-
sible to generate at all, that is an insight into the underlying model.
An additional case study could provide even more context. In 2019, while
studying the FFHQ dataset that was used to generate images of human faces
for StyleGAN, I noted that the faces of black women were consistently more
distorted than the faces of other races and genders. I asked the same question:
What data was present to make white faces so clear and photorealistic? What
data was absent to make black women’s faces so distorted and uncanny? I began
to formulate a hypothesis. In the case of black women’s faces being distorted, I
could hypothesize that black women were underrepresented in the dataset: that
this distortion was the result of a weak signal. In the case study of kissing cou-
ples, something else is missing. One hypothesis might be that the dataset used
by OpenAI does not contain many images of anyone kissing. That might explain
the awkwardness of the poses. I might also begin to inquire about the absence of
same-sex couples and conclude that LGBTQ couples were absent from the dataset.
While unlikely, we may use this as an example of how to test that theory, or what-
ever you find in your own samples, in the next step.

5. Connect these Patterns to Corresponding Strengths and

Weaknesses in the Underlying Dataset

Each image is the product of a dataset. To continue our research into interpreting
these images, it is helpful to address the following questions as specifically as
possible:
1. What is the dataset and where did it come from?
2. What can we verify what is included in the dataset and what is excluded?
3. How was the dataset collected?
Often, the source of training data is identified in white papers associated with
any given model. There are tools being developed – such as Matt Dryhurst and
Holly Herndon’s Swarm, that can find source images in some sets of training data
(LAION) associated with a given prompt. When training data is available, it can
confirm that we are interpreting the image-data relationship correctly. OpenAI
trained DALL·E 2 on hundreds of millions of images with associated captions. As
of this writing, the data used in DALL·E 2 is proprietary, and outsiders do not have
access to those images. In other cases, the underlying training dataset is open
source, and a researcher can see what training material they draw from. For the
sake of this exercise, we’ll look through the LAION dataset, which is used for the
diffusion engines Stable Diffusion and Midjourney. When we look at the images

IMAGE | 37(1), 2023 93

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

that LAION uses for “Photograph of humans kissing”, we can see that the training
data for this prompt in that library consists mostly of stock photographs where
actors are posed for a kiss, suggesting a database trained on images displaying
a lack of genuine emotion or any romantic connection. For GAN models, which
produce variations on specific categories of images (for example, faces, cats, or
cars), many rely on open training datasets containing merely thousands of imag-
es. Researchers may download portions of them and examine a proportionate
sample. This may become exponentially harder as datasets become exponentially
larger. For examining race and face quality through StyleGAN, I downloaded
the training data – the FFHQ dataset – and randomly examined a sub-portion of
training images to look for racialized patterns. This confirmed that the propor-
tion of white faces far outweighed faces of color.
While we do not have training data for DALL·E 2, we can make certain inferenc-
es by examining other large datasets. For example, we might test the likelihood
of a hypothesis that the dominance of heterosexual couples in stock photography
contributes to the relative absence of LGBTQ subjects in the images. This would
explain the presence of heterosexual couples (a strong signal from the dataset) and
the absence of LGBTQ couples that occurred in our earlier tests from 2022. How-
ever, LAION’s images found for the prompt query “kissing” is almost exclusively
pictures of women kissing. While DALL·E 2’s training data remains in a black box,
we now have at least some sense of what a large training set might look like and
can recalibrate the hypothesis. The massive presence of women kissing women in
the dataset suggests that the weak pattern is probably not a result of sparse train-
ing data or a bias in data. We would instead conclude that the bias runs the other
way: if the training data is overwhelmed with images of women kissing, then the
outcomes of the prompt should also be biased toward women kissing. Even in the
October 2022 sample, however, women kissing women seemed to be rare in the
generated output.
This suggests we need to look for interventions. An intervention is a system-lev-
el design choice, such as a content filter, which prevents the generation of certain
images. Here we do have data even for DALL·E 2 that can inform this conclusion.
‘Pornographic’ images were explicitly removed from OpenAI’s dataset to ensure
it does not reproduce similar content. Other models, such as LAION, contain vast
amounts of explicit and violent material (cf. Birhane 2021). By contrast, OpenAI
deployed a system-level intervention into their dataset:
We conducted an internal audit of our filtering of sexual content to see if it concentrated or
exacerbated any particular biases in the training data. We found that our initial approach
to filtering of sexual content reduced the quantity of generated images of women in gen-
eral, and we made adjustments to our filtering approach as a result (OpenAI 2022: n.pag.).
Requests to DALL·E 2 are hence restricted to what OpenAI calls ‘G-rated’ con-
tent, referring to the motion picture rating for determining age appropriateness.

IMAGE | 37(1), 2023 94

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

Figure 5: First page of screen results from a search of LAION training data associated
with the word “Kissing” indicates a strong bias toward images of women kissing, Screen
grab from haveibeentrained.com [Accessed March 22, 2023]

G-rated means appropriate for all audiences. The intervention of removing

images of women kissing (or excluding them from the data-gathering process)
as ‘pornographic’ content reduced references to women in the training data.
The G-rating intervention could also explain the barrier effect between kissing
faces in our sample images, a result of removing images where kissing might be
deemed sexually charged. We may now begin to raise questions about the criteria
that OpenAI drew around the notion of ‘explicit’ and ‘sexual’ content. This leads
us to new sets of questions helpful to forming a consecutive hypothesis.
1. What are the boundaries between forbidden and permitted content in the
model’s output?
2. What interventions, limitations, and affordances exist between the user
and the output of the underlying dataset?
3. What cultural values are reflected in those boundaries?
Next is to test these questions. One method is to test the limits of OpenAI’s
restricted content filter which prevents the completion of requests for images
that depict pornographic, violent, or hateful imagery. Testing this content filter,
it is easy to find out that a request for an image of “two men kissing” creates an
image of two men kissing. Requesting an image of “two women kissing” triggers
a warning for “explicit” content (this is true as of February 2023). This offers a
clear example of mechanisms through which cultural values become inscribed
into AI image production. First, through the dataset: what is collected, retained,

IMAGE | 37(1), 2023 95

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

and later trained on. Second, through system-level affordances and/or interven-
tions: what can and cannot be produced or requested.

6. Re-examine the Original Image of Interest

We now have a hypothesis for understanding our original image. We may decide
that the content filter excludes women kissing women from the training data as
a form of ‘explicit’ content. We deduce this because women kissing is flagged as
explicit content on the output side, suggesting an ideological, cultural, or social
bias against gay women. This bias is evidenced in at least one content moderation
decision (banning their generation) and may be present in decisions about what
is and is not included in the training data. The strangeness of the pose in the ini-
tial image, and of others showing couples kissing, may also be a result of content
restrictions in the training data that reflect OpenAI’s bias toward, and selection
for, G-rated content. How was ‘G-rated’ defined, however, and how was the data
parsed from one category to another? Human, not machinic, editorial process-
es were likely involved. Including more ‘explicit’ images in the training model
likely wouldn’t solve this problem – or create new ones. Pornographic content
would create additional distortions. But in a move to exclude explicit content,
the system has also filtered out women kissing women, resulting in a series of
images that recreate dominant social expectations of relationships and kisses as
‘normal’ between men and women.
Returning to the target image, we may ask: What do we see in it that makes
sense compared to what we have learned or inferred? What was encoded into the
image through data and decisions? How can we make sense of the information
encoded into this image by the data that produced it? With a few theories in
mind, I would run the experiment again: this time, rather than selecting images
for the patterns they shared with the notable image, use any images generated
from the prompt. Are the same patterns replicated across these images? How
many of these images support the theory? How many images challenge or com-
plicate the theory? Looking at the broader range of generated images, we can
see if our observations apply consistently – or consistently enough – to make
a confident assertion. Crucially, the presence of ‘successful’ images does not
undermine the claim that weak images reveal weaknesses in data. Every image
is a statistical product: odds are weighted toward certain outcomes. When you
see successful outcomes fail, that failure offers insight into gaps, strengths, and
weaknesses of those weights. They may occasionally – or predominantly – be
rendered well. What matters to us is what the failures suggest about the underly-
ing data. Likewise, conducting new searches across time can be a useful means of
tracking evolutions, acknowledgments, and calibrations for recognized biases.

IMAGE | 37(1), 2023 96

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

As stated earlier, my sampling of AI images from DALL·E 2 conducted showed

swings in bias from predominantly white, heterosexually coded images toward
greater representations of genders and skin tones.
Finally, we may conclude that AI generated images of couples kissing is the
result of technical limits. Lips kissing may reflect a well-known flaw in render-
ing human anatomy. Both GANs and Diffusion models, for example, frequently
produce hands with an inappropriate number of fingers. There is no way to
constrain the properties of fingers, so they can become tree roots, branching in
multiple directions, multiple fingers per hand with no set length. Lips, too, can
seem to be more constrained, but the variety and complexity of lips, especially in
contact with each other, may be enough to distort the output of kissing prompts.
Hands and points of contact between bodies – especially where skin is pressed or
folds – are difficult to render well.

Discussion & Conclusion

Each of these hypotheses warrants a deeper analysis than the scope of this paper
would allow. The goal of this paper was to present a methodology toward the
analysis of generative images produced by Diffusion-based models. Our case
study suggests that examples of cultural, social, and economic values are embed-
ded into the dataset. This approach, combined with more established forms
of critical image analysis, can give us ways to read the images as infographics.
The method is meant to generate insights and questions for further inquiry,
rather than producing statistical claims, though one could design research for
quantifying the resulting claims or hypotheses. The model has succeeded in
generating strong claims for further investigations interrogating the underly-
ing weaknesses of image generation models. This includes the absence of black
women in training datasets for StyleGAN, and now, the exclusion of gay women
in DALL·E 2’s output. Ideally, these insights and techniques move us away from
the ‘magic spell’ of spectacle that these images are so often granted. It is intend-
ed to provide a deeper literacy into where these images are drawn from. Identi-
fying the widespread use of stock photography, and what that means about the
system’s limited understanding of human relationships, emotional and physical
connections, is another pathway for critical analysis and interpretations.
The method is meant to move us further from the illusion of ‘neutral’ and
unbiased technologies which is still prevalent in the discourse around these
tools. We often see AI systems deployed as if they are free of human biases – the
Edmonton police (Canada) recently issued a wanted poster including an AI-gen-
erated image of suspect based on his DNA (cf. Xiang 2022). That’s pure mystifi-
cation. They are bias engines. Every image should be read as a map of those biases,

IMAGE | 37(1), 2023 97

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

and they are made more legible using this approach. For artists and the general
public creating AI-images, it also points to a strategy for revealing these prob-
lems. One constraint of this approach is that models can change at any given
time. It is obvious that OpenAI could recalibrate their DALL·E 2 model to include
images of women kissing tomorrow. However, when models calibrate for bias
on the user end it does not erase the presence of that bias. Models form abstrac-
tions of categories based on the corpus of the images they analyze. Removing
access to those images, on the users end, does not remove their contribution to
that abstraction. The results of early, uncalibrated outcomes are still useful in
analyzing contemporary and future outputs. Generating samples over time also
presents opportunities for another methodology, tracking the evolution (or lack
thereof) for a system’s stereotypes in response to social changes. Media studies
may benefit from the study of models that adapt or continuously update their
underlying training images or that adjust their system interventions.
Likewise, this approach has limits. One critique is that researchers cannot
simply look at training data that is not accessible. As these models move away
from research contexts and toward technology companies seeking to make a
profit from them, proprietary models are likely to be more protected, akin to
trade secrets. We are left making informed inferences about DALL·E 2’s proprie-
tary dataset by referencing datasets of a comparable size and time frame, such
as LAION 5B. Even when we can find the underlying data, researchers may use
this method only as a starting point for analysis. It raises the question of where
to begin even when there are billions of images in a dataset. The method marks
only a starting point for examining the underlying training structures at the
site where audiences encounter the products of that dataset, which is the AI-pro-
duced image.

Thanks to Valentine Kozin and Lukas R.A. Wilde for feedback on an early draft of this essay.

Bibliography

Barthes, Roland: Image, Music, Text. Translated by Stephen Heath. London

[Fontana Press] 1977
Birhane, Abeba; Vinay Uday Prabhu; Emmanuael Kahembwe: Multimodal
Datasets: Misogyny, Pornography, and Malignant Stereotypes. arXiv:2110.01963.
October 5, 2021. https://arxiv.org/abs/2110.01963 [accessed February 16, 2023]
Chandler, Daniel; Rod Munday: A Dictionary of Media and Communication. Oxford
[Oxford University Press] 2011
Hall, Stuart: Encoding/Decoding. In: Culture, Media, Language: Working Papers in
Cultural Studies, 1972-1979. London [Routledge] 1992, pp. 117-127

IMAGE | 37(1), 2023 98

Eryk Salvaggio: How to Read an AI Image: Toward a Media Studies Methodology for the Analysis of Synthetic Images

Hall, Stuart: The Work of Representation. In: Representation: Cultural

Representations and Signifying Practices. London [Sage] 1997, pp. 15-74
Harris, Robert: Information Graphics: A Comprehensive Illustrated Reference. New York
[Oxford University Press] 1999
OpenAI: DALL·E 2 Preview – Risks and Limitations. In: GitHub. July 19, 2022.
https://github.com/openai/dalle-2-preview/blob/main/system-card.md
[accessed February 16, 2023]
Offert, Fabian; Thao Phan: A Sign That Spells: DALL-E 2, Invisual Images and the
Racial Politics of Feature Space. arXiv:2211.06323. October 26, 2022. https://arxiv.
org/abs/2211.06323 [accessed February 20, 2023]
Ramesh, Aditya; et al.: Zero-Shot Text-to-Image Generation. arXiv:2102.12092.
February 24, 2021. https://arxiv.org/abs/2102.12092 [accessed February 16, 2023]
Rose, Gillian: Visual Methodologies: An Introduction to Researching with Visual
Materials. London [Sage] 2001
Salvaggio, Eryk: How to Read an AI Image: The Datafication of a Kiss.
In: Cybernetic Forests. October 2, 2022. https://cyberneticforests.substack.com/p/
how-to-read-an-AI-image [accessed February 16, 2023]
Xiang, Chloe: Police are Using DNA to Generate Suspects they’ve Never Seen.
In: Vice Media. October 11, 2022. https://www.vice.com/en/article/pkgma8/
police-are-using-dna-to-generate-3d-images-of-suspects-theyve-never-seen
[Accessed February 18, 2023]

IMAGE | 37(1), 2023 99