Shoulder Carry: CapCut vs AI, other tools and prompts

Where a prompt struggles with this scene

• What you type: a general tool wants a prompt and settings. MimicZip has no prompt box; you add your photos and choose the options.
• Your look: a general tool often changes the faces or the sizes of the two bodies when they are in contact; our scene is built to hold yours.
• The beats: the carry, the turn, the landing and the pose need the right order, and we fix the order for you.
• Nothing borrowed: the prompt never names a song or an account, which many tools filter anyway.
• Cost: general tools run on their own plans. MimicZip has packs from $8.99, 1 credit per clip and previews in each pack.

When a general tool is better

Use a general tool for your own story or full camera control. Use MimicZip when you want exactly this clip from your photo, fast: a carry across the shoulders, a turn on the spot and a gentle landing in front of the camera. To write the prompt yourself, see Kling, Veo and Seedance.

Copy this prompt

Image-to-video, 9:16, about 9 seconds.
Reference image 1 is the carrier and reference image 2 is the carried; keep each one's species, face, hair or fur, markings, clothes and body shape exactly in every second. Exactly two subjects, never swapped, never merged. A pet can only be the carried one.
Setting: a plain underground car park with a low ceiling and strip lights, cool even light; each one in the clothes from their own photo. One continuous take, a fixed camera at chest height, both in frame from head to knees, vertical.
0-2 s: the carrier faces the camera with the carried lying relaxed across both shoulders.
2-4 s: the carrier turns around slowly on the spot, the carried swings gently and lifts their head.
4-7 s: the carrier bends the knees and lowers the carried gently onto their feet in front, who turns to face the camera (a pet is lowered into the arms).
7-9 s: the carried strikes a proud pose in front, the carrier smiles behind.
Nobody falls, nothing is thrown, nobody is hurt. No text, numbers or logos anywhere. Audio: a light instrumental beat, no vocals. Natural colour, no subtitles, no logos, no watermark.

How to use it

• Attach two photos: the carrier (an adult) and the carried one (an adult or a small pet) as the reference image(s).
• Add your sound in TikTok afterwards. A text prompt cannot place each beat exactly, so expect to shift the sound.
• Leave names, sound titles and brands out. Tools can filter them, so the prompt describes the action instead.
• Tools change often, so check the length and aspect ratio your tool supports and adjust the first line.

Copy this prompt

Create a 9-second cinematic video from the reference image, 9:16.
Reference image 1 is the carrier and reference image 2 is the carried; keep each one's species, face, hair or fur, markings, clothes and body shape exactly in every second. Exactly two subjects, never swapped, never merged. A pet can only be the carried one.
Setting: a plain underground car park with a low ceiling and strip lights, cool even light; each one in the clothes from their own photo. One continuous take, a fixed camera at chest height, both in frame from head to knees, vertical.
0-2 s: the carrier faces the camera with the carried lying relaxed across both shoulders.
2-4 s: the carrier turns around slowly on the spot, the carried swings gently and lifts their head.
4-7 s: the carrier bends the knees and lowers the carried gently onto their feet in front, who turns to face the camera (a pet is lowered into the arms).
7-9 s: the carried strikes a proud pose in front, the carrier smiles behind.
Nobody falls, nothing is thrown, nobody is hurt. No text, numbers or logos anywhere. Audio: a light instrumental beat, no vocals. Natural colour, no subtitles, no logos, no watermark.

How to use it

• Attach two photos: the carrier (an adult) and the carried one (an adult or a small pet) as the reference image(s).
• Add your sound in TikTok afterwards. A text prompt cannot place each beat exactly, so expect to shift the sound.
• Leave names, sound titles and brands out. Tools can filter them, so the prompt describes the action instead.
• Tools change often, so check the length and aspect ratio your tool supports and adjust the first line.

Copy this prompt

Generate a 9-second 9:16 video using the reference image as the subject.
Reference image 1 is the carrier and reference image 2 is the carried; keep each one's species, face, hair or fur, markings, clothes and body shape exactly in every second. Exactly two subjects, never swapped, never merged. A pet can only be the carried one.
Setting: a plain underground car park with a low ceiling and strip lights, cool even light; each one in the clothes from their own photo. One continuous take, a fixed camera at chest height, both in frame from head to knees, vertical.
0-2 s: the carrier faces the camera with the carried lying relaxed across both shoulders.
2-4 s: the carrier turns around slowly on the spot, the carried swings gently and lifts their head.
4-7 s: the carrier bends the knees and lowers the carried gently onto their feet in front, who turns to face the camera (a pet is lowered into the arms).
7-9 s: the carried strikes a proud pose in front, the carrier smiles behind.
Nobody falls, nothing is thrown, nobody is hurt. No text, numbers or logos anywhere. Audio: a light instrumental beat, no vocals. Natural colour, no subtitles, no logos, no watermark.

How to use it

• Attach two photos: the carrier (an adult) and the carried one (an adult or a small pet) as the reference image(s).
• Add your sound in TikTok afterwards. A text prompt cannot place each beat exactly, so expect to shift the sound.
• Leave names, sound titles and brands out. Tools can filter them, so the prompt describes the action instead.
• Tools change often, so check the length and aspect ratio your tool supports and adjust the first line.