JME format channel / 15 seconds

Dito Ang Tingin AI Video Generator

Turn two authorized photos into a Dito Ang Tingin AI video. One person performs from the café booth while the other leans into the frame from behind, joining the expressions, gestures, and musical exchange.

Scene

Teal café booth · two-person musical interaction

The show video previews the seated opening, the second performer's entrance, and the shared expressions and hand gestures. Your two uploaded subjects replace the original performers.

  • Two required photos
  • Seated and behind-the-booth roles
  • Warm café setting
  • 15s · 9:16 · 720p

Two photos · 15s · café duet

JME freestyle homeWatch demos

Independent AI format. Not affiliated with any artist, song, original performers, platform, or label. Generated music and vocals are original.

Image-to-video control desk Input live

Required · photo 1 stays seated in the foreground. Use a clear adult portrait.

Required · photo 2 leans into the shot from behind. Use a clear adult portrait.

By generating, you confirm you are 18 or older, have permission to use the uploaded photos and the subjects’ likenesses, and agree to our Terms and Privacy Policy.

Prohibited content

Do not upload photos you are not authorized to use. See the full Acceptable Use Policy for details. View Acceptable Use Policy

Duration15s300 credits

Aspect ratio

9:16

This template is vertical (9:16). 16:9 would require stretching the scene, so it is not offered.

Or buy a One-Time Pass without an account: 720P · 15s · one successful video. Choose your template and photos after payment.

Use credits

Sign in / Account · Same account and credits as JME freestyle.

This video costs: 300 credits

Upload the seated performer first, then the partner who leans into the frame from behind.

Credit packs are on Pricing. View history

Output reel

Dito Ang Tingin demos

Dito Ang Tingin · Demo 1

Format guide

What is the Dito Ang Tingin AI video?

This Dito Ang Tingin template turns two portraits into a playful café performance. The scene opens on one person seated in a teal restaurant booth. A second person leans into the shot from behind and joins the musical interaction. The performance follows the reference expressions, head movements, and hand gestures while replacing both source performers with your uploaded subjects.

Two photos, two fixed roles

Photo 1 becomes the seated performer closest to the camera. Photo 2 becomes the partner who enters from behind the booth. Keeping the roles fixed helps the interaction remain readable as both people share the frame. Upload exactly two authorized adult portraits; neither the original performers nor background diners are intended to remain in the generated scene.

How to make your Dito Ang Tingin video

Watch the example, upload your two photos in role order, and confirm the image permissions and consent requirements. Start the 15-second generation using your credits. The existing generator handles the combined reference image, task progress, result preview, and download. The output uses a vertical 9:16 frame at 720p, with newly generated music and vocals.

Photo tips for a natural café duet

Choose sharp, well-lit portraits showing one adult per image. Keep the face, mouth, and hairstyle unobstructed, and include upper-body clothing where possible. Avoid group photos, strong beauty filters, and extreme profile angles. Clear photos support recognizable faces, but expression timing, hand anatomy, lyrics, and mouth synchronization can vary between generated results.

Questions

Dito Ang Tingin FAQ

How many photos does this template need?

Exactly two adult portraits. Photo 1 becomes the seated foreground performer; photo 2 becomes the partner leaning into the shot from behind.

Does the second person appear from the start?

The prompt follows the reference sequence: a seated opening, followed by the partner leaning into the frame and joining the performance. Generated timing may vary.

Will the original people stay in the video?

The template instructs the model to replace both source performers with your uploaded subjects and remove background faces.

Does it include the original song?

The generation instructions request new original music and vocals. They do not request a copy of the source song, lyrics, recording, or identifiable performer voices.

What size and length is the result?

The generated output is 15 seconds in vertical 9:16 at 720p. The uploaded show video is a reference example and may have a different duration.