When a prompt leaves details unspecified, a generated output still contains particular people, settings, objects, and styles. Those results can be shaped by learned parameters, training and fine-tuning data, filtering, ranking, interface defaults, prompt interpretation, and sampling—not by the prompt alone.
Test whether the output centers a white or light-skinned, male-presenting, nondisabled adult—and which identities do not appear across repeated samples.
Look for a hospital corridor or exam room, then compare with clinics, field hospitals, home visits, and non-Western settings.
Ask whether the doctor is centered as an authority and whether patients, colleagues, or care teams are absent or backgrounded.
Track whether a stethoscope, white coat, clipboard, or tablet appears without being requested.
Compare realistic or aspirational brochure lighting with documentary, informal, or community-care imagery.
Observe whether expertise work is foregrounded while administrative, emotional, or caregiving labor is underrepresented.
Test whether the output centers an older white, male-presenting, formally dressed figure—and who is missing across repeated samples.
Look for a corner office, boardroom, branded stage, or skyline, then test other kinds of workplaces.
Ask whether leadership appears as solitary authority or as listening, collaboration, and distributed decision-making.
Track unrequested status cues such as a dark suit, watch, podium, conference table, or elevated viewpoint.
Compare high-contrast profile imagery with candid, collaborative, or less polished depictions.
Observe whether the figure speaks and directs more often than they listen, collaborate, or learn.
Watch for racialized, gendered, or age-coded bodies. One run cannot establish prevalence; a documented audit requires repeated samples, a named system, and a comparison baseline.
Track whether urban streets, alleys, low light, or other danger-coded settings appear without being requested.
Ask whether the person is framed as threatening or decontextualized and whether guilt is visually assumed rather than evidenced.
Record unrequested props such as weapons, masks, or hoodies and how they are used to signal threat.
Compare dramatic shadow and menacing framing with neutral or contextualized visual treatment.
Observe whether the action depicts threat while omitting legal, social, or narrative context.
Test whether the output favors a two-parent, different-gender nuclear family and which family structures are absent across repeated samples.
Look for suburban, leisure, or living-room settings, then compare urban, rural, multigenerational, and informal homes.
Track whether adult roles and caregiving labor are assigned through familiar gender conventions.
Record consumer goods that signal class and note which economic contexts the output does not depict.
Compare warm aspirational advertising with documentary, ordinary, or less polished family imagery.
Observe whether the scene emphasizes harmony and abundance while omitting stress, conflict, work, or ordinary monotony.
Images, captions, and labels influence learned parameters. Their effect is mediated by the training objective and later system layers.
Media, stock photography, textbooks, and journalism contain prior conventions that may enter datasets and product design.
Fine-tuning, safety filters, style presets, ranking, interfaces, and post-processing can change what users receive.
An underspecified prompt leaves more decisions unresolved. Specificity can shift outputs but does not isolate one causal layer.
The Diffusion Step-Through Viewer is an authored teaching model of iterative denoising. The Image Default Test Board helps you document what a named system produced, what changed after one prompt revision, and which causal claims remain unverified.