PROMPT · Image Generation
Cinematic Coffee Shop Night Portrait
A short GPT-Image 2 demo that turns an ordinary portrait into a cinematic rainy-night coffee shop scene. Two samples are shown, one of the same woman seated holding a takeaway cup, one standing with a shoulder bag, both lit by warm streetlamps against a wet pavement and a coffee shopfront with hand-painted signs. The full prompt is referenced in the replies rather than embedded in the post, so this entry captures the visual recipe and the prompt's intent, not the prompt text itself.
Here's the thing.
@AiwithLariab (Laraib Fatima) dropped a four-line post with two samples and a one-line verdict. "AI Cinematography Magic." Turn ordinary photos into stunning cinematic visuals. The tool, GPT-Image 2 inside ChatGPT.
Then "Prompt👇" and the actual prompt text isn't in the post itself, it's tucked into the replies.
What the samples show, even without the prompt text in hand, is a clear visual recipe.
The same young woman, both shots. Long dark hair, round wire glasses, soft pink lips, the kind of gentle off-center smile that doesn't quite land at the camera. Outside a coffee shop on a rainy city night. Warm streetlamps throw long reflections across the wet pavement. In one she's seated at a small table, both hands wrapped around a takeaway cup. In the other she's standing with a shoulder bag, coat slightly opened, a half-step out of the doorway.
The shopfront itself carries the scene. A hand-painted chalkboard sign reads "Good Coffee Better Days." In the seated shot a wall to the right reads "Some Stories Heal You." In the standing shot a banner overhead reads "A Brighter You Ahead." Small typographic details, but they do real work selling the mood.
The visual cues worth keeping for anyone who wants to replicate the look, soft warm streetlamp key light, wet pavement as a second light source, umbrellas and pedestrians slightly out of focus in the background to set depth, low color temperature overall with the takeaway cup and signage as warmer accents, film-grain texture rather than a clean render, a lens feel that's slightly wide and intimate without being distorted.
Heads up on the source. The post text ends with "Prompt👇" and that's it, the prompt itself sits in the reply thread rather than the body, and our fetch script doesn't read replies. So this entry documents the visual recipe and the prompt's intent, not the verbatim prompt text. To grab the actual prompt, head into the original thread and read the first reply yourself.
At the time of writing, the post sits at 20 likes, 1 bookmark and 498 views, a quiet one. Original thread here, x.com/AiwithLariab/status/2096573378077561202
