One new apple-holder
Your adult photo replaces the person; the original macaque remains separate.
A macaque grabs a red apple from an adult on a forest path, followed by a push-in on the surprised face.
Monkey Eating Apple AI casts one adult in a forest-path skit. The person starts with a red apple, the macaque on the stone railing reaches for it, and a brief tug of war ends with the animal taking it.
Your photo replaces only the apple-holder. Their face, hair, body appearance and visible clothes follow the reference performance, while the macaque keeps its own identity and movements.
The camera ends by pushing toward the person's surprised face. This version follows the complete selected take, about 9.1 seconds, and delivers a vertical 9:16 video at 720p with that reference's original audio.
The red apple ties the scene together. The adult's hands and the macaque's paws meet at the same prop before the animal wins it. A clear view of your face and upper body helps the reaction remain readable during the final close-up.
The stone railing, sunny path and macaque stay from the reference. You do not supply an animal photo, and your clothes do not move onto the macaque. This page has one adult role rather than a two-person remake.
The original preview is 540 × 962, very close to 9:16. The finished video uses 9:16 without stretching the person or animal. Review the apple contact and the face in the push-in before saving.
Your adult photo replaces the person; the original macaque remains separate.
Keep the bite, tug of war and surprised reaction in their original order.
The person keeps the visible clothes from your photo in the fixed forest scene.
Add one clear adult photo with the face and upper body visible.
Generate this single-person scene for 10 credits.
Watch the apple, both sets of hands and the final face before downloading.
Only the adult holding and eating the red apple. The macaque keeps its original identity, size and movements.
No. This version takes one adult photo and retains the macaque from the reference. It has no second-person or animal-photo slot.
Your visible clothes, face, hair and body appearance come from the photo. The forest path, railing, light and camera come from the reference.
The adult bites the apple, the macaque grabs it and wins a short tug of war, then the camera pushes in on the adult's surprised face.
The tool creates a video scene from your photo. You do not need to approach or feed an animal.
About 9.1 seconds in 9:16 at 720p, with the original audio from the selected short reference. The source preview keeps its actual 540 × 962 frame.
The single-person video costs 10 ReelTada credits. Your balance is checked before photo upload or a generation request.
One bite becomes a tug of war. Put your photo in the apple-holder's role while the macaque on the stone railing keeps the scene moving.