PromptFeed
Photography & Realism

Surveillance Feed: Defiant Shopper

A gritty, degraded CCTV-style still of a defiant figure caught mid-gesture inside a cluttered retail shop.

Minimum tier: free5 editable variables
Surveillance Feed: Defiant Shopper

Image generated by us with gpt-image-2. Prompt by @xmliisu

Prompt

A heavily distorted, low-fidelity surveillance-style image shows [SUBJECT_APPEARANCE] standing behind a cramped checkout counter inside a cluttered [SHOP_TYPE], captured from a high-mounted camera angled steeply downward in a top-down CCTV perspective. The image quality is intentionally degraded, with strong motion blur, digital smearing, compression artifacts, heavy noise, scan lines, and subtle fisheye distortion warping the frame edges, making fine details indistinct and stretched. The subject is centered from mid-torso upward, looking up toward the camera with the head tilted back; facial features are largely obscured by blur and artifacts, though [SUNGLASSES_COLOR] oversized sunglasses dominate the face, reflecting ambient light, and the mouth appears open with the tongue faintly visible. One hand is raised toward the camera with the middle finger extended, clearly readable in silhouette but softened and ghosted by motion and low clarity, conveying a relaxed yet defiant posture. The foreground counter is cluttered with papers and a [BAG_COLOR] shopping bag with rope handles, while the background shelves are densely packed with small items, souvenirs, and figurines that blend into abstract shapes due to low resolution and noise. Harsh, flat fluorescent lighting produces blown highlights, dull shadows, uneven color reproduction, and a [COLOR_CAST] color cast with visible banding and reduced dynamic range. Despite an effectively deep depth of field, perceived sharpness remains low, reinforcing a raw, gritty, confrontational mood that emphasizes the authenticity of an unpolished, unenhanced surveillance feed in a vertical 4:5 aspect ratio.

5 placeholders still empty. Copied as is, the generator will draw the brackets literally inside the image.

Editable variables

Change any value and the prompt rewrites above. Copy the finished result.

text

How the person looks: build, hairstyle, clothing.

text

The kind of retail shop the scene takes place in.

color

Color or finish of the oversized sunglasses.

color

Color of the shopping bag on the counter.

color

The overall tint of the degraded surveillance footage.

Generate the image here

With your own OpenAI key. Free for us, and what you spend is yours.

Kept in this browser only and sent straight to OpenAI's API: it never passes through a server of ours, because there is no server of ours in between. Check it yourself in the network tab.

Fill in the remaining variables before generating, or the model will draw the brackets.

Similar cases