Make the "your next opponent is you" video with your younger self
Hey, it's Cindy 🌱 This is the full walkthrough from the reel: the cinematic "your next opponent is you" video, made from just two photos of you, one as a kid and one now.
btw the waitlist for AI System Club is now open! If you're keen on using AI to automate your content, video editing, job search, business or build AI agents, feel free to sign up (only if you want to hehe). Ps. the waitlist gets first dibs:)
the outcome
What you are making
A 10 to 15 second cinematic video: your younger self climbs up into a single spotlight beam, looks around, and then stands across from present-day you in the darkness. It reads like a movie scene because the prompt forbids everything that makes AI video look like AI video: no camera movement, no extra lights, no changing framing.
before you start
What you need
📸 Two photos of you: one as a kid, one recent. Clear face, decent lighting. Full body helps but isn't required, the model mostly needs identity and outfit
🎬 A Higgsfield account, the video model is Seedance 2.0 (it's the one that can hold TWO people from reference photos in the same scene)
✂️ CapCut (free) for the finishing layer: grain, the text, and the voice line
the build
The steps
🌐 Go to higgsfield.ai, hit Generate, then Create video
🧠 Switch the model to Seedance 2.0 (standard mode goes up to 1080p and 4K; Seedance 2.0 Mini is the cheaper, faster version if you're testing)
🖼 Upload your two photos: younger you first, current you second (the order matters, the prompt references image 1 as the child and image 2 as you now)
📝 Paste the prompt below, then rewrite the two character descriptions so they match what's actually in YOUR photos (age, hair, exact outfit). The model follows your words as much as your photos, so describing the real outfits keeps the identity locked
⏱ Set the length (10 seconds is the sweet spot, Seedance goes up to 15), pick 9:16 for reels, and generate
🎞 Finish in CapCut: add film grain, the caption text, and the voice line
copy this
The prompt
Paste this, then customize the two character blocks:
🎬 the full cinematography prompt
15-second cinematic video, absolutely no camera movement, no zoom, no pan in any shot. Complete darkness throughout. One single dramatic light source in the entire video, a single angled spotlight beam coming from the upper right corner, cutting through the darkness at a diagonal angle, illuminating both figures simultaneously in all shots. No other light sources exist anywhere. Two characters: <<<image_1>>> YOUNGER GIRL, [describe YOUR childhood photo: age, height, hair, exact outfit, shoes]. <<<image_2>>> OLDER YOUNG WOMAN, [describe YOUR recent photo: age, height, hair, exact outfit, shoes].
SHOT 1 (0-5 sec): Static medium shot framed from chest to waist, never changes. One single diagonal spotlight beam from upper right corner cuts through the darkness. At the start the YOUNGER GIRL is below the frame, completely hidden in darkness. She slowly climbs upward, rising from the darkness into frame, entering the diagonal light beam and becoming illuminated. Slight breathlessness, tense nervous posture. She looks around cautiously. Raises her eyes upward toward the light, squints, lifts one hand to shield her eyes. Pauses. Slowly lowers her hand and looks directly forward. Pure dark void background.
SHOT 2 (5-10 sec): Static wide shot, framing never changes. Same single diagonal spotlight beam from upper right corner illuminating both figures. Camera faces forward. YOUNGER GIRL stands LEFT FOREGROUND with her BACK to the camera on a very low gentle mound, closer to camera. OLDER YOUNG WOMAN stands FAR BACKGROUND on the RIGHT on a slightly higher gentle mound, facing toward camera, completely still, hair moves very slightly. Vast darkness everywhere else.
SHOT 3 (10-15 sec): Static wide side-angle shot, framing never changes. Same single diagonal spotlight beam from upper right corner. LEFT side: YOUNGER GIRL on lower gentle mound, seen from side, facing right, still. RIGHT side: OLDER YOUNG WOMAN on slightly higher gentle mound, seen from side, facing left, still. Both full body visible, large distance between them. Deep darkness surrounding both. Cinematic, moody, atmospheric.
(Adjust GIRL/WOMAN wording to whoever is in your photos. If you generate at 10 seconds, the model compresses the three shots to fit, which is what the original creators do.)
the craft
Why this prompt works
Steal these rules for any cinematic AI video:
🚫 It forbids instead of asks "Absolutely no camera movement, no zoom, no pan" and "no other light sources exist anywhere" remove the drifting-camera, over-lit look that screams AI
💡 One light source, stated twice The single diagonal spotlight is described in every shot, so the model never invents a second light
🎬 Shots with timestamps Blocking the video into SHOT 1/2/3 with exact seconds and "framing never changes" gives you an edit, not a clip
🧍 Emotional stage directions, not vibes "Squints, lifts one hand to shield her eyes, pauses" is actable direction the model can follow, better than "she looks emotional"
the last 10%
The finishing layer
The AI video is 90% there, the last 10% sells it:
🎞 Film grain in CapCut (search "grain" in effects, keep it subtle)
💬 The text: "Congratulations, you're moving to the next level. Your next opponent is you." Timed so "your next opponent is you" lands when both of you are in frame
🔊 The voice line: use the trend's original audio on Instagram so the reel joins the trend's audio page, or generate the line with an AI voice if you want your own spin