Build me a single AI video prompt for [tool] that produces a usable shot on the first try.
TOOL: {Runway Gen-3 / Pika 2 / Kling / Luma Dream Machine}
WHAT I WANT TO SEE (plain English): {your_idea}
MOOD / GENRE: {cinematic / surreal / horror / nature-doc / commercial / anime / etc.}
MOTION I WANT IN THE SHOT: {what_moves — subject, camera, environment, none}
LENGTH: {seconds — usually 4-10}
ASPECT: {16:9 / 9:16 / 1:1}
GENERATE A PROMPT THAT INCLUDES, IN THIS EXACT ORDER:
1. **Subject** (who/what is in frame, with 2-3 specific visual descriptors)
2. **Action** (1 specific motion, written as a verb)
3. **Environment** (where it is — 2 descriptors)
4. **Light** (source, quality, direction — 'overcast morning, soft, from screen-left')
5. **Camera & lens** (35mm, 50mm, 85mm, anamorphic, wide, telephoto)
6. **Camera movement** ('static', 'slow dolly-in', 'handheld', 'truck right')
7. **Mood / color reference** (Tarkovsky, Wong Kar-wai, Roger Deakins, Edward Hopper, A24, 90s VHS, etc.)
8. **Motion qualifiers** ('slow gentle', 'subtle', 'no fast motion')
RULES:
- ≤80 words.
- Don't use 'beautiful', 'amazing', 'stunning'.
- Don't ask for text, faces with specific identities, or copyrighted characters.
- Avoid impossible camera moves (e.g. 360° around a fast-moving object — these break).
- Pick ONE color palette anchor (don't list 5 references — pick 1).
ALSO PROVIDE:
- **What to expect:** 1 line explaining what the tool tends to get RIGHT in this kind of prompt and what it might get WRONG.
- **First retry adjustment:** if the first generation isn't good, what specific word to change.0 copies·0 saves·5 views
260 words·1,605 chars
Sample output
TOOL: Runway Gen-3 Idea: A woman runs through a foggy forest at dawn. Mood: Cinematic dreamy, slightly melancholic Length: 6 seconds, 16:9
PROMPT (78 words):
A woman in her late 20s wearing a long dark green coat and brown leather boots, dark hair loose, runs steadily through a dense pine forest at dawn, low mist hovering knee-height, cool early morning light filtering through the trees from screen-right, 35mm cinematic, handheld camera following at her hip level slightly behind her, subtle motion blur, muted blue-green color palette in the style of Roger Deakins, slow gentle pace, no fast motion, atmospheric stillness around her movement.
What to expect: Runway Gen-3 is excellent at atmospheric forest + dawn light, and it handles 'handheld following a runner' well at slow paces. It tends to GET WRONG: the boots (often morphs them to wrong shape mid-shot) and the coat color (can drift between green and grey). It tends to GET RIGHT: the mist, the light direction, and the overall film-like grain.
First retry adjustment: If the runner's motion looks robotic or sped-up, change 'runs steadily' to 'jogs slowly' — Runway interprets 'runs' as fast-action and overcompensates with cartoonish gait.
Parameters
Text generation parameters
FAQ
Keep your prompts under 80 words. Beyond that, AI video models start ignoring the back half. Build the prompt in the exact order listed — these tools weight the first 3 elements (subject/action/environment) heaviest. The prompt targets ChatGPT (GPT-4) and lives in the Writing & Content category on mycopyprompt.
This prompt is written for ChatGPT (GPT-4). It's a text/chat prompt — paste it into ChatGPT (GPT-4) (or compatible LLMs like Claude or GPT-4) to get the expected output.
1. Click the Copy button on this page to copy the full prompt. 2. Open ChatGPT (GPT-4). 3. Paste the prompt into a new conversation. 4. Replace any {placeholders} with your specifics, then send. Most prompts produce the right output on the first try; complex ones may need 1-2 iterations.
Yes — every prompt on mycopyprompt is free forever. No paywall, no signup wall for browsing or copying. You can use it for personal or commercial work, just don't redistribute the entire mycopyprompt library.
Absolutely — most prompts are templates. Look for {placeholders} (curly braces) and swap them with your own values. You can also reword sections, add constraints, or chain it with other prompts.
See the "Sample output" panel above — that's a real example of what ChatGPT (GPT-4) returns when this prompt runs. Your output will vary in wording but should follow the same structure and depth.
Similar prompts
Matched against every prompt in the catalog by title.