ImageGenerate

Create a rainy monochrome noir scene

Build an invented film-still composition with a small anonymous figure, wet paving and directional street lighting. Customize the coat and urban setting.

Tools: ChatGPT built-in image generation

What to provide

Describe non-branded clothing for the fictional anonymous adult.
Keep a plausible outdoor street setting with wet paving.

Make it yours

Fill in what you know. Empty fields stay as placeholders.

Subject outerwear

Describe non-branded clothing for the fictional anonymous adult.

Nighttime street setting

Keep a plausible outdoor street setting with wet paving.

Your prompt

/noir /night /filmstill Create a landscape 3:2 black-and-white cinematic still from an imaginary film. Show a lone anonymous adult wearing a long coat and carrying a closed umbrella, walking away along a rain-soaked city street at night. Frame the person small in the middle distance beneath a single bright streetlamp, with deep shadows, wet pavement reflections, a faint mist and restrained fine film grain. Use an eye-level wide composition with strong leading lines and enough shadow detail to distinguish the figure from the background. Make the scene quiet and mysterious, with no violence or weapons. The person is fictional and has no identifiable real likeness; this is newly generated artwork, not a frame from an existing movie. No readable signs, text, subtitles, logos, watermarks or slash-label lettering.

Ready to copy

Example Recorded test output

Input

Recorded inputs (2026-10-28): Subject outerwear: long coat Nighttime street setting: rain-soaked city street These defaults expand to the exact prompt used for the saved output. No reference image was supplied.

Output

Recorded AI-generated output from the exact default inputs. Reflected light separates the figure from the background. The output expands the brief into a riverside streetscape with extra lamps and architecture.

AI-generated monochrome noir scene of a lone figure on a wet street beneath a streetlamp — Result

Tool settings

Actual recorded run: 2026-10-28. Built-in image_gen tool; model name, seed and quality setting were not exposed. Opaque background. Saved PNG: 1536 × 1024. No reference image. Layout directions in the template describe the requested composition, not guaranteed output settings.

Improve the result

Keep the figure size, wet paving and monochrome treatment. Remove the extra lights so one streetlamp dominates the scene.
Inspect the result at full size and at its intended display size. Recheck text, object structure and any changed details.

Use this prompt

Keep the default inputs to copy the exact recorded generation prompt, or customize the fields for a new variation. Copy the completed text into an image-capable tool. New inputs and follow-ups are untested variations.

About the example

Reflected light separates the figure from the background. The output expands the brief into a riverside streetscape with extra lamps and architecture.

Newly generated fiction, not a real event or an existing film frame. The scene does not follow every composition constraint literally; small revisions may change unrelated details.

The slash labels are informal creative shorthand. This example was produced by built-in image generation; no model name was exposed.

Technology, explained

Ideas into practice