Rain on a window with city bokeh with a prompt built for Sora and Veo. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the details and treat the result as a structured draft, not a final answer.
4.8(21 ratings)171 copies
Updated By Author
44 words · v1.2
Sora promptReplace every highlighted token before sending
Close-up of raindrops sliding down a window at night, city lights rendered as soft bokeh behind. Warm and cool colours mixed, slow focus pull from the glass to the street. 50mm, f/1.4, shallow depth of field. 6 seconds, 16:9. Audio: rain and muffled traffic. One continuous shot, no cuts, no text overlays. Duration 5 seconds.
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open Sora and start a new chat. Paste the prompt exactly as written.
2
Replace the bracketed context with your own facts. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. First and last frames for artefacts, audio for unwanted speech, and the model's commercial terms.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Example shot brief: Rain window city bokeh
Example output
Generate one shot only: the subject moves at a natural pace while the camera performs a single controlled move. Keep lighting consistent from first to last frame. Review the first and last frames for morphing, then check hands, faces and any signage. If continuity breaks, shorten the action or reduce camera movement rather than adding more description. Assemble longer sequences in an editor.
Tips for a better result
One shot and one action per generation. Build sequences in the edit, not in the prompt.
Name the camera move explicitly and keep it physically simple.
Generate at the final aspect ratio to avoid cropping away the composition.
Ask for one targeted revision rather than a full regeneration; it preserves what already works.
Common mistakes
Asking for multiple events, locations or characters in a single short clip.
Expecting legible text, logos or complex hand interactions to render correctly.
Using a reference image or voice you do not have rights to use.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the rain on a window with city bokeh prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
A video prompt for fitness rep in a home gym. It gives Sora and Veo a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the context, run it once, then use the verification notes on this page to review the result.
This copy-ready video prompt helps you product unboxing hands-only with fewer blank-page decisions. Paste it into Sora and Runway, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
This copy-ready video prompt helps you cinematic product loop for a hero section with fewer blank-page decisions. Paste it into Sora and Veo, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
SoraVeoRunway
4.7(14)240 copies
A
Written and reviewed by Author
AIPrompt123 Contributor
Contributing author and prompt engineer at AIPrompt123.
Last reviewed 17 November 2026 · version 1.2 · tested on Sora, Veo, Pika
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.