Jean Phil AI prompt: a free copy-paste prompt for the deadpan suit boxer.
Want to make the Jean Phil trend yourself? Below is a complete, original prompt for an image-to-video model: you in a vintage suit, totally deadpan, shadowboxing on a quiet street. There's a face-off version for two, a line-by-line explanation, photo tips and fixes for the usual fails. Don't want to tune prompts? Use the one-click generator instead.
In short
To make a Jean Phil-style AI video, give an image-to-video model one clear photo of yourself and a prompt that asks for: a sharp three-piece suit, a completely expressionless face, crisp shadowboxing jabs on a quiet European street, and a slow punch toward the camera, in 9:16. The key words are “deadpan” and “expressionless” — without them the model smiles. Copy the prompt below, or skip the tuning with duet.room's Jean Phil AI generator.
Don't want to tune prompts?
Use the Jean Phil AI (suit boxer) generator: upload a photo, get the video — the prompt is already tuned. Full videos $6.99 per video, no subscription.
Open the Jean Phil AI (suit boxer) generatorCopy-paste prompts
Works in any image-to-video model that accepts reference photos (Kling, Seedance, Hailuo, Runway and others): attach the photos in order, paste the prompt, choose 9:16 and 5–10 seconds.
Solo (one photo)
A 10-second vertical 9:16 cinematic shot, slightly desaturated film look, static camera, full body in frame. The person from [IMAGE 1] wears a sharp, slightly old-fashioned three-piece suit and tie; keep their face and hairstyle exactly as in the photo. Setting: a quiet European-style city street with stone buildings, soft overcast light. 0–3 s they stand perfectly still, completely deadpan and expressionless. 3–8 s precise shadowboxing — two jabs, a hook, light footwork — face never changes. 8–10 s one slow punch straight toward the camera lens, then they straighten their tie, still deadpan. Deadpan comedy, nobody is hit, no text on screen, no logos. Original minimal tense instrumental, no vocals.
Face-off (two photos)
A 10-second vertical 9:16 cinematic shot, slightly desaturated, static camera, full body. The person from [IMAGE 1] and the person from [IMAGE 2] both wear sharp three-piece suits and face each other in boxing stances a few steps apart; keep both faces and hairstyles exactly as in their photos. Setting: a quiet European-style stone street, overcast light. 0–3 s they stare at each other, completely deadpan. 3–7 s they trade slow, theatrical air punches and dodges without ever touching. 7–10 s both stop, straighten their ties and stare at the camera, expressionless. Nobody is hit, no text, no logos. Original minimal tense instrumental, no vocals.
What each line does
| Prompt line | Why it's there |
|---|---|
| “vertical 9:16 … static camera, full body in frame” | TikTok/Reels format, and the full body keeps the footwork visible. A moving camera makes the jabs look messy. |
| “three-piece suit and tie … keep their face and hairstyle exactly as in the photo” | Changes the outfit but protects your identity. Without the second half many models redraw the face. |
| “completely deadpan and expressionless … face never changes” | The whole joke. Models default to smiling; say it twice. |
| “quiet European-style city street … overcast light” | Gives the old-film mood without copying any real clip or location. |
| “two jabs, a hook, light footwork” and timestamps | Concrete moves and times give you a readable sequence instead of random flailing. |
| “nobody is hit, no text, no logos” | Keeps the result safe for every platform and avoids garbled on-screen text. |
Which photo to use
- One person per photo, face clearly visible, looking roughly at the camera.
- Waist-up or full body works best; avoid tight selfies taken from below.
- No sunglasses, no heavy filters, good even light.
- Use your own photo or one of a friend who agreed — not the original Jean Phil character or any public figure.
Common fails and how to fix them
| Problem | Fix |
|---|---|
| They keep smiling | Repeat “completely deadpan, expressionless, face never changes” and remove words like “fun” or “playful” from the prompt. |
| The face drifts away from the photo | Use a sharper, front-facing photo and keep “keep their face exactly as in the photo”. Shorter clips (5 s) drift less. |
| Punches look like flailing | Name the moves (jab, hook) and give time ranges; ask for a static camera. |
| In the face-off they actually hit each other | Say “a few steps apart … without ever touching” and “nobody is hit”. |
| Random text or signs appear | Add “no text on screen, no logos”; plain stone streets work better than shop fronts. |
Don't want to tune prompts?
Use the Jean Phil AI (suit boxer) generator: upload a photo, get the video — the prompt is already tuned. Full videos $6.99 per video, no subscription.
Open the Jean Phil AI (suit boxer) generatorQuestions people ask
Is this the official Jean Phil prompt?+
No. It's our own original prompt for the same deadpan suit-boxer look. It doesn't use the original character's face, videos or accounts, and we're not affiliated with its creators.
Which AI video tool should I use with it?+
Any image-to-video model that accepts a reference photo — Kling, Seedance, Hailuo, Runway and similar. Or skip the setup and use duet.room's Jean Phil AI generator, which already uses a tuned version of this prompt.
Can I add the trending sound?+
Yes — add it in TikTok or Reels when you post. The prompt asks for an original instrumental so your video isn't muted.
How long should the video be?+
5–10 seconds is the sweet spot: long enough for the jabs and the slow punch, short enough that the face stays consistent.