The Virumi team
Two people or pets trade rap gestures around a hanging microphone in an orange booth.
Photos and roles
Use two photos, one subject in each. Photo one takes the left position and photo two the right. Each position can use a person or pet; clear faces or muzzles and visible upper bodies help the close-ups and gestures.
Use a sharp original photo rather than an enlarged screenshot. Keep one intended subject in each subject slot, with even lighting and no stickers or heavy face coverings. Check the role labels before replacing a photo so the same image does not accidentally fill two different parts.
What happens in the video
- Two performers take their left and right positions in the orange booth.
- They share the hanging microphone through alternating gestures and rap delivery.
- Close-ups and wider shots follow the two performers without changing their roles.
- The pair finish the routine together on the musical ending.
Choose the version
The performance lasts 14 seconds in a 4:3 frame, with a hanging microphone and the scene soundtrack. Both roles are required, whether you choose people, pets or a mixed pair.
The creation form shows the options available for the selected version. Review its photo requirements, duration, audio choice and quote together. A sample shown for one cut or resolution does not establish the result of every other combination.
Make and review the video
- Open the template and choose an available version.
- Add the photos in their labeled roles and review any optional scene settings.
- Check the current quote, duration and audio setting before submitting.
- When the result is ready, watch the entire clip, including the transitions and ending.
- Download the completed video and check its audio in the downloaded file.
Check the left/right photo mapping before following the camera cuts. Look for consistent faces or pet features, readable gestures and a microphone that remains part of the booth rather than merging into a subject.
Common questions
Which photos should I use?
Use two photos, one subject in each. Photo one takes the left position and photo two the right. Each position can use a person or pet; clear faces or muzzles and visible upper bodies help the close-ups and gestures.
Which version should I choose?
The performance lasts 14 seconds in a 4:3 frame, with a hanging microphone and the scene soundtrack. Both roles are required, whether you choose people, pets or a mixed pair.
What will my video cost?
The selected version, model and resolution determine the current quote. Check the displayed duration and total before submitting; a price from a different template or version does not apply automatically.
Will the result match the example exactly?
Check the left/right photo mapping before following the camera cuts. Look for consistent faces or pet features, readable gestures and a microphone that remains part of the booth rather than merging into a subject. AI motion and fine details can vary. A reference example explains the scene; it is not a guarantee for every input photo.
View the template and its available examples.
Newly opened options have not completed a Virumi generation trial. Reference previews do not demonstrate tested output quality.