Genjutsu AI - Recast Music Videos with Your Characters

Turn an MV trend into your own AI music video. Upload two character photos and a reference clip, then follow its dance, performance, and camera cuts with your chosen cast.

0/1
0/1
0/1
choose Ref video· or upload your own file
optional - 0/1

0/6000

How to Create an AI Music Video with Genjutsu AI

Start with an MV trend or performance you want to imitate. AnyMimic takes the source video as the guide for movement and camera changes, while the two required photos specify the replacement performers.

1

Select an MV Trend or Music Video Clip

Pick the part of a music video you want to mimic or choose the included APT example. If it exceeds the reference limit, trim to the dance, interaction, or camera sequence that matters most.

2

Upload Two Character Images

Fill both required image fields with clear photos. Assign each photo to one original performer so the model knows whose appearance to replace in the MV.

3

Describe the Replacement Roles

Edit the prompt to match Image 1 and Image 2 to the correct people in the video. Follow those identities through camera cuts and side changes while keeping the original MV background.

4

Make and Preview Your AI MV

Choose the available video and audio settings, review the credit estimate, and generate. Compare the output with the reference for movement, expressions, camera framing, and character consistency.

An MV Trend Is a Full Performance, Not a Still Image

Two photos cannot show how an MV’s performers dance, interact, or move through different shots. Reproducing those beats by filming again takes choreography, a location, and editing.

Side Labels Stop Working after a Cut
A performer who starts on the left may switch sides or appear alone later. A fixed left/right instruction can become ambiguous.
Portrait Backgrounds Can Distract
The image setting may have no connection to the music video. The model needs separate instructions for character appearance and the scene it should follow.
Long Sequences Expose More Drift
A fast montage gives less time to read facial detail and more opportunities for the two replacement identities to blur together.
Image 1

Genjutsu AI Turns an MV Reference into Your Cast’s Performance

AnyMimic uses the selected music video for choreography, setting, and camera direction. Two uploaded photos tell the model whom to put in the original performers’ places.

Give each required field one photo so you can inspect who appears in each role. Faces and outfits with clear details are easier to compare in a preview.

The source shows how performers move, gesture, turn, and respond to one another. A different video produces a different performance plan.

The reference provides lighting, props, background, and camera direction. Portraits provide character identity rather than replacing the scene.

Check role assignments at cuts, during overlaps, and in solo moments. Revise the prompt or source segment if a generated take confuses the cast.

Make an MV Trend Your Own with Genjutsu AI

Use a familiar duet or another music video as the reference, then try your own pair in its performance. Review a short AI MV before deciding how to finish or share it.

Create an AI Music Video with Your Pair
Place two people you know or two original characters into a shared stage performance using images you may use.
Try a Duo MV Trend
Choose a two-person trend and give each original performer a replacement image. Review both identities as they move or trade positions.
Try a New Visual World
Pick footage with the camera angles and setting that fit your concept, whether it is a studio, street, or another filmed scene.
Compare Dance Moves and Camera Cuts
Compare the generated version with your chosen reference to see where performance beats hold or change.
Iterate on One Performer
Retain the video and one image while testing another character photo for the second role.
Prepare a Shareable Edit
Download the preferred output and finish captions or cleared music in your normal editing workflow.

Plans & pricing

Standard Pack

$10

15 credits with a one-time payment

Unlock longer video generation durations

No subscription required

No recurring charges

Plus Pack

$30

60 credits with a one-time payment

Unlock longer video generation durations

No subscription required

No recurring charges

Mega Pack

$80

200 credits with a one-time payment

Unlock longer video generation durations

No subscription required

No recurring charges

Credits explain

480p video generation costs approximately 1 credit per second — about 15 credits for a 15-second video.

Different models have different generation costs.

The corresponding consumption will be calculated and displayed next to the generate button on the generation page.

Genjutsu AI FAQ

Understand the inputs, limits, and practical checks before generating.