CreatorHeisenberg →A surrealist prompt for capturing a wide drone photo of a giant man, with his face and body based on a reference image, casually sitting on a London street. The scene emphasizes the scale contrast between the enormous human figure and the tiny urban elements around him, rendered in soft overcast daylight.
View original source ↗
Prompt
A photorealistic wide drone shot of a colossal man (exact face/body from the reference) casually sitting across a London street, one knee raised, hand resting. He wears a navy overcoat, knit sweater, dark trousers, boots, and a minimalist beanie. Tiny cars, buses, bikes, and pedestrians move around him, with classic London red-brick buildings, black lamps, and cobblestone streets dwarfed by his size. Soft overcast London daylight highlights wet pavement.
Reusable method
Key decisions
Check whether the subject, style, and material constraints all hold in the final result.
Adapt it to your subject
Extract “target result → the subject, scene, material, and color palette → constraints” as a reusable template for similar work.
Where it breaks
Run single-variable comparisons around subject description, style intensity, lighting, and material constraints. Record the model, cost, and failures; turn it into a Skill only after it repeats reliably.
Recommended models
Creator
Heisenberg focuses on AI image making and is active on X. “Giant Seated Figure on a London Street” is the current representative case, built with GPT Image 1.5 with its stability retest open to votes.
Keep exploring
A prompt requesting a specific composition: a photo featuring two people, Sam and Ilya, and a dog. The specified style is “2000s film-camera style,” with the mood “looking very bored at a children’s birthday party.”
Prompt
Combine the two men (Sam & Ilya) and the dog in a 2000s film camera-style photo of them looking bored at a kids birthday party.
A highly detailed and complex prompt designed to create a seamless 16:9 composite image divided into four distinct quadrants, each representing a different brand (Luckin Coffee, Google, Coca-Cola, McDonald's), using an exquisite paper-cut aesthetic, specific structural requirements, and Octane rendering.
Prompt
A seamless 16:9 full-frame composite image divided into four distinct quadrants. **CRITICAL:** The four sections touch each other directly. NO GREY BACKGROUND. NO BORDERS. NO GAPS.
A custom prompt designed to make AI-generated images look more realistic by imitating raw, candid, amateur smartphone photography. It specifies technical details such as lens, aperture, and lighting, and includes aesthetic instructions such as “boring reality” and “tiny imperfections” to achieve an unretouched, low-contrast look.
Prompt
1:1 aspect ratio Raw Realistic candid natural amateur photo, background in focus, amateur candid photography, Captured on {argument name="camera model" default="Samsung Galaxy S21
