One singer or two new performers
Replace only the left singer, or add a second photo to cast the keyboard player as well.
The singer tips its head upward while the watch-wearing corgi plays the keyboard through close and wide music-room shots. 14 seconds.
The Mabel Matiz Umrumdışı AI piano trend pairs a singer looking upward with a pianist at a black keyboard. In this reference, a tabby cat sings on the left and a corgi wearing a wristwatch plays on the right. A cream bowl sits in front of the keyboard, and guitars hang on the music-room wall.
Choose Singer Solo to replace the left singer with one photo while the corgi pianist stays in the scene. Choose Duet and add a second photo to replace the pianist too. The two uploaded subjects keep their separate roles through close views and wider classroom shots.
Each photo can show an adult who agreed to appear, your pet, a toy or a character you have permission to use. The photo supplies the subject’s whole appearance. The selected clip supplies the singing gestures, keyboard movement, scene, cuts and timing. The finished MP4 lasts 14 seconds in vertical 9:16 at 720p.
Singer Solo is a one-photo setup. Your subject takes the left singer’s place, lifts its head and follows the expressive mouth and body movements from the reference. The corgi on the right keeps its own appearance, wristwatch and keyboard performance. Your photo does not spread onto the pianist.
Duet uses two separate photos. Photo 1 always sings on the left; Photo 2 always plays the keyboard on the right. The pianist follows the hand or paw movements and wears the scene’s wristwatch where its limbs allow. This is a two-role performance, even when one subject briefly fills more of the frame.
An adult keeps a human body, hair and visible clothes. A pet keeps its species, muzzle, fur pattern and paws. A toy or character keeps its own shape, colors and material. The tool is asked to replace the whole subject, so a person should not inherit the reference cat’s body.
The reference is a short performance with a ceiling-facing singer and an attentive pianist. It uses the original reference sound after the picture is generated. Mouth movements follow the visible reference performance; the page does not offer separate lyric entry or phoneme-by-phoneme lip-sync controls.
Replace only the left singer, or add a second photo to cast the keyboard player as well.
Keep an adult’s outfit, a pet’s markings or a toy’s distinctive shape while following the reference action.
Keep the music room, keyboard, cuts and selected reference audio in a 14-second vertical MP4.
Add the singer as Photo 1. For Duet, add the pianist as Photo 2. Use one clear subject per image.
Confirm your permission to use the subjects and start. A low balance opens the credit-pack dialog before generation.
Check the singer, the keyboard contact and the cut to the wider scene. Download the video with reference sound.
It puts the subjects from your photos into a short music-room performance: a singer on the left and a pianist on the right. It is also searched as Umrum Dışı, Umrumdisi and the Yan Sen Derdine cat piano trend.
Singer Solo takes one photo for the left singer and keeps the corgi pianist from the reference. Duet takes two photos: Photo 1 is the singer, and Photo 2 replaces the pianist.
Yes. Use one clear photo of your pet, preferably showing its whole body and paws. The pet keeps its species, face, coat and markings while taking the selected role.
Use a photo showing the whole figure and a character you have permission to use. Its shape, material, colors and style provide the subject’s appearance, rather than a cat body from the reference.
Use a clear photo of one consenting adult, from the waist up or full body, with the face and clothes visible. The subject should keep adult proportions rather than the reference animal’s size.
The pianist on the right follows the reference wristwatch detail when its arms or legs allow it. In Singer Solo that pianist remains the corgi; in Duet the second photo supplies the pianist.
Mouth movement follows the singing motion visible in the reference. There is no separate lyric field or exact phoneme control. Review the mouth and the long-note expression in the finished clip.
The downloaded MP4 is 14 seconds, vertical 9:16 at 720p. The reference plays at its original pace, including the changes between close and wide shots.
Yes. The finished MP4 uses the audio from the exact selected 14-second reference. Check the rights to the recording and song before publishing it or using it in an advertisement.
This template uses its fixed music-room reference, keyboard and shot sequence. The background in your subject photo does not replace the classroom, and there is no custom reference-video field.
Each generation costs 10 credits in either mode. If your current balance is below 10, the page opens a credit-pack dialog before starting generation.
Return to this template or My creations to check the existing task. Failed tasks show the error and return the task credits automatically. Reopening the page checks the saved task rather than requiring a new generation.
Choose your singer, add a pianist if you want, and bring their own looks into the music room.