Video trend
Two thirds of this clip is a face or a mouth at very close range, so small mistakes are big on screen. Generation follows instructions; it does not guarantee them. Before you post, watch the video three times with sound: once for the face, once for the mouth and once for anything left over. This page lists what to look at and when to re-run.
This is the only stretch where the whole face is on screen. Pause around 4 seconds and compare with your photo: eyes, nose, hairline, facial hair. If someone else is looking back at you, re-run with a sharper, more front-facing photo.
"You're not that guy, pal" sits around 2.5 to 4 seconds and "trust me, you're not that guy" around 4 to 5.5 seconds. The open vowels and the closed "m" of "me" are the easiest checks. A small drift is normal; words landing a whole syllable late is a re-run.
Around 5.5 to 6 seconds the lips should be shut. A mouth that keeps moving through the pause looks like a voice-over, not a person.
Only the nose tip, mouth and chin should be in shot. Look for a second mouth, eyes appearing at the top edge, melting teeth or skin that changes tone. Stubble and lips should match your photo.
Your own outfit should be there from the first frame. Look for a stray red cape edge, gold shoulder pieces, coloured gloves, grey patches or thin cyan lines from the motion guide, especially at the edges of the frame during camera movement. Any of these is a re-run.
Re-run for a wrong face, a second mouth, costume pieces or guide leftovers. Post when the face is yours, the lips land on the line and the close-up is clean. Label it as AI-made and only post videos of people who agreed to be in them.
Add a photo for each role shown below. All roles need a photo.
Add one clear photo of yourself or of someone who agreed to appear. A sharp, front-facing face with the mouth and chin clearly visible works best, because the last three seconds are a close-up of the lower face. The outfit in the photo is the one you wear.
Choose 480p, 720p or 1080p and review the quote. It includes the full video and the photo preparation.
Watch your face on "you're not that guy, pal" around 3 seconds, the closed-lip pause near 5.5 seconds and your mouth in the final close-up, then download your vertical MP4.
From about 2 seconds your face rises into the camera frame and fills it by 5 seconds. From 6 seconds the phone drops to an extreme close-up of your mouth and chin for the rest of the clip, so your lips, stubble or beard and skin carry the last three seconds.
The reference performer wears a blue superhero suit with a red cape. That costume is not part of the template: you wear the outfit in your photo, and the cape, armour and gloves are left out.
"You're not that guy, pal. Trust me, you're not that guy." Your video keeps the clip's original audio and timing; you do not record anything, and your photo does not change the voice.
One continuous 9-second handheld shot through a bright pharmacy, no cuts. The preview is the reference clip, not an Oakgen result.
It is a 9-second vertical AI video built on the "You're not that guy, pal" meme audio. One person faces an offscreen camera operator in a pharmacy as the camera tilts up and moves closer. The visible person says "you're not that guy, pal, trust me, you're not that guy", ending in an extreme close-up of their mouth and chin. Oakgen's template puts the person from your photo in it and keeps the store, the camera moves and the audio.
"You're not that guy, pal" is a meme from a viral 2020 video filmed in a store, later reused as a sound and a catchphrase for telling someone they are less impressive than they think. The reference clip pairs that audio with a man dressed as Homelander from The Boys. This template is an unofficial fan-style format, not connected to the show, the meme's original video or any store.
No. The suit, cape, shoulder armour and gloves in the reference are not kept. Your photo replaces the whole person, so you wear the outfit in your photo. A plain T-shirt or a work shirt often makes the line funnier.
No. The video keeps the clip's original audio, so you are heard in the meme's voice. You do not record anything.
Yes, one, and it is required. The person in the reference is never kept, so your photo always takes the role.
That is the joke of the clip: the phone gets so close that only the lower face is left in frame for the last three seconds. Your face is fully on screen from about 3 to 6 seconds; after that the template keeps the same extreme close-up.
Use photos of yourself or of people who agreed to be in the video. Do not upload photos of actors, celebrities or anyone who has not consented, label AI videos clearly when you share them and keep the put-down obviously a joke.
The template sends the clip's audio and the tracked mouth movement of the reference with your photo, and the original audio is restored at the end. These are instructions to a model, so check the close-ups before posting and re-run if the lips clearly drift.
The template is written for a person talking into a phone. An animal photo is not blocked, but the result is untested and the mouth close-up may not look right.
9 seconds in portrait 9:16, one continuous handheld take with no cuts.
No. It is the reference clip the trend comes from, not an Oakgen result. Review the face, the mouth close-up and the hands in your video before sharing.
1,798 credits per 720p video. The quote includes the photo preparation and the complete video. Check it before generating.
Plan a story, keep your character recognizable, and make the finished clip your own.
Make the You're Not That Guy, Pal AI video step by step: pick who to cast and which photo, read the quote, check the mouth close-up and post your 9-second clip.
Where "you're not that guy, pal" comes from, why the superhero version took off, why it gets funnier on a real friend and how the AI template rebuilds the clip.
Upload 1 photo. Everything else is set.