AI image generated from the “Cinematic Street Photography Portrait” prompt
Result produced with GPT Image 2 · @frametheory058

Cinematic Street Photography Portrait

The prompt1863 chars
Create an ultra-realistic cinematic street photography portrait of me on a busy city street. Keep my face exactly the same as in the reference photo — same facial structure, eyes, nose, lips, hairstyle, skin tone, proportions, and overall identity. Do not alter, beautify, or reinterpret my appearance in any way.

I am standing confidently in the center of the frame wearing an oversized black hoodie, relaxed cargo pants, and casual streetwear. My expression is playful, slightly mischievous, and natural, as if I’m proudly showing my creative side.

I’m holding a large white poster board in front of me.

The poster should contain only ONE hand-drawn sketch illustration of me. No multiple portraits or variations.

The sketch should be:

Black-and-white pencil drawing

Highly detailed

Realistic facial resemblance

Expressive line art

Artist sketchbook style

Clean white background

Subtle shading

Visible hand-drawn pencil strokes

Confident creator energy

At the bottom of the sketch, write:

[Name]

Around the sketch, add only a few minimal doodles:

Tiny stars

Small hearts

Paper airplane

Light sketch arrows

Subtle creative marks

Keep the poster simple, clean, and powerful.

The mood should feel creative, inspiring, authentic, artistic, and documentary-like, as if it’s part of a creator movement campaign.

Style: ultra-realistic street portrait, natural lighting, shallow depth of field, soft background blur, premium editorial photography, magazine-quality image, cinematic storytelling, Pinterest aesthetic, creator-brand campaign, emotional and relatable, professional photography, 8K masterpiece.

The contrast between the real me and the hand-drawn sketch version of me should be the main visual focus, creating a strong artist-versus-art effect. The single sketch on the poster must remain the clear focal point.

Aspect ratio: 4:5

Swap these placeholders

  • Name

Replace each bracketed token with your own subject before generating — leaving them in place makes the model render the literal words.

Credit

Collected from EvoLinkAI/awesome-gpt-image-2-API-and-Prompts · originally shared by @frametheory058.