Why this prompt works
The prompt succeeds through specificity of subject and environment, creating a relatable urban scene. The detailed clothing description and smartphone action give the model clear focus points. Without these cues, the AI might generate generic passengers without clear subject emphasis. The technical specifications like 'f/1.8' and '35mm lens' guide the model toward cinematic depth of field and realistic optical qualities.
This scene tells a story of urban isolation within a crowd, with the woman absorbed in her digital world despite being surrounded by people. The contrast between her focused behavior and the passive commuters creates visual tension that reads well on screen. The shallow depth of field emphasizes her while blurring the background passengers, enhancing this narrative.
The prompt components map directly to rendering elements: 'ultra-realistic' and 'photorealistic' guide detail levels, 'warm fluorescent lighting' sets color temperature, 'subtle film grain' adds texture, and '35mm lens, f/1.8' creates the characteristic bokeh. For 5 seconds, expect 2-3 seconds establishing shot, 2 seconds subject focus, then subtle environmental movement. Model-agnostic phrases like 'natural skin texture' help avoid uncanny valley results.
This prompt works well for social media clips exploring digital-age isolation, urban life documentaries, or background ambiance in films. Pair with exterior establishing shots of the subway system or cut to close-ups of the smartphone screen to create narrative continuity. Works well with montages showing different people in similar urban isolation scenarios.
Prompt anatomy
- Subject
- young woman in dark green and burgundy hoodie
- Action
- quietly looking at smartphone on subway
- Setting
- crowded subway train interior
- Camera
- implied - add one for more control
- Lighting & mood
- warm fluorescent lighting, documentary-style
Make it yours
- 1For more dynamic framing, add 'medium shot from eye level' to better establish subject-background relationships while maintaining the shallow depth of field effect.
- 2To avoid common AI failure modes of distorted hands or unnatural smartphone interactions, specify 'realistic hand holding phone' and 'natural screen glow'.
- 3For Instagram Reels compatibility, add 'vertical composition' and consider extending to 7-9 seconds to allow for subtle head movement or environmental changes.
- 4If using Midjourney, add '--style raw' parameter for more realistic skin textures and avoid the default illustration tendency.
Realistic Subway Train Crowd Interior
Ultra-realistic cinematic scene of a young woman standing inside a crowded subway train, quietly looking at her smartphone while passengers sit and stand around her. She wears a dark green and burgundy hoodie over a white shirt, with a backpack over one shoulder. Warm fluorescent train lighting, realistic urban atmosphere, shallow depth of field, cinematic composition, natural skin texture, soft background bokeh, subtle film grain, documentary-style photography, 35mm lens, f/1.8, high detail, photorealistic, vertical.
How to use this video prompt
- Click "Use this prompt" — it loads into the text-to-video generator automatically.
- Pick a model, aspect ratio and duration (or keep the recommended settings above).
- Hit generate — free users get daily free generations, no watermark.
Tip: swap the subject or setting and keep the camera, lighting and style parts — that's the structure that makes these prompts work.
Need a matching cover image for your video? Reverse-engineer any image into a prompt →