Your photo is where the story starts
This is an effect preview. You can check progress and watch your finished video in My Videos.
Use this templateLoading…
AI Old Town Road Video
Restoring draft…
- Estimated time
- 5–15 minutes
- Credit cost
- Loading…
Credits are automatically returned if generation fails due to a technical problem.
Your finished MP4 will be saved in My Videos, where you can play and download it.
Loading…
Use photos and likenesses you have permission to use.
Try More Viral Videos
What is AI Old Town Road?
Cast two people in a red convertible music-video scene. The driver appears beside the open window, the singer takes the solo close-ups, and both reappear in an overhead shot before the car leaves. The roughly 14.7-second reference keeps its pace, with a brief road-only tail for the 15-second output.
- What your photos control
- Photo 1 controls the driver beside the steering wheel, including the opening greeting and final overhead view. Photo 2 controls the singer in every solo shot and the passenger in the final two-person view. Camera angles never change these bindings.
- Movement and background
- AI generates a new clip from the example’s routine and setting. Backgrounds, camera movement, expressions and occlusion may vary; frame-for-frame matching is not guaranteed.
Photo to video: a paired example
Compare the input photos with their corresponding video to assess the subject’s appearance and movement.
What happens in this video?
Three frames from this template’s showcase explain the scene and performance.
01 · Opening Meet the driver
The camera moves beside the windshield toward the driver, who rests an arm on the door and raises a hand toward the forehead.
02 · Middle Cut to the singer
The passenger performs alone in medium and tighter close-ups, nodding and lifting open palms in front of a colorful shop.
03 · Later Leave in the convertible
An overhead view reunites the driver and passenger before the red car moves out of the frame, leaving an empty road.
How to get a better result
Recommended photos
- Upload two separate, sharp single-person photos with visible faces and hairstyles.
- Show shoulders and clothing to guide the driver’s raised hand and the singer’s palm gestures. Use the driver-first, singer-second order.
- Even lighting and clear detail
- A subject outline distinct from the background
Try to avoid
- Collages, chat interfaces or watermarked screenshots
- Group photos, heavy filters or faces obscured by a phone, dark glasses, hair or deep shadow.
- Tight face-only crops that hide the outfit, shoulders or raised-arm shape.
- Blur, darkness or heavy filters
If the result needs improvement
- The appearance looks different
- Try separate unobstructed portraits with even lighting and visible hair. The driver is seen from the side and above, while the singer turns and leans toward the lens; heavy filters and shadows make these angles harder.
- Limbs or props connect awkwardly
- Show shoulders, arms and the outfit where possible. The driver’s hand near the forehead, palms near the singer’s face and contact with the money bag are difficult details and may vary.
- Roles or positions get mixed up
- Check the driver-first, singer-second upload order. The middle solo close-ups must use photo 2; photo 1 stays at the steering wheel in the opening and overhead shots.
- The movement or performance differs
- The reference guides the gestures, camera changes and car departure. Lip movements, hands and likeness can vary. Its original pace is retained; only the road-only ending is briefly held to reach 15 seconds.
- The task reports a generation failure
- Check the task status in My Videos first. Technical failures return deducted credits automatically; a successful video that does not meet personal expectations is a different situation. Each new generation costs credits, so review the refund policy before retrying.
How to Make a AI Old Town Road Video
- Step 01
Upload your photos
Upload two separate person photos, following the role order.
- Step 02
Generate your video
Choose 480p / 720p / 1080p, confirm the credits, and submit. The current output is 15 seconds in 16:9. You can leave the page while it processes, then check My Videos when ready.
- Step 03
Download and share
When ready, play and download the MP4 from My Videos and save a copy to your device.
My Videos
FAQ
Which photo is the driver and which is the singer?
Photo 1 is the driver at the steering wheel. Photo 2 is the singer in the solo close-ups and the passenger in the overhead shot. Upload one person in each photo; the roles do not swap when camera angles change.
Do both people keep their own faces and outfits?
Each photo guides its person’s face, age, hair, build and visible clothing. The prompt does not add the original performers’ cowboy hats, sunglasses, beards or Western outfits unless present in the uploads. Generated details can still vary.
What kind of photo works best?
Use two clear, evenly lit single-person photos, with visible eyes, hair, shoulders and clothing. Put the driver first and singer second. Avoid a group shot or a face hidden by dark glasses or a phone.See photo guidance for this effect ↓
Is this preview a generated customer result?
Yes. This generated example uses the two portraits shown here: the gray striped-sweater person is the driver, and the blue-cap person in a brown jacket is the singer and passenger. Your own photos follow the same role order; generated details may vary.
Will the result keep the appearance in my photos?
The first photo stays tied to the driver and the second to the singer, including the final overhead view. Their original faces, hairstyles and outfits guide generation throughout; exact likeness is not guaranteed.
What duration and aspect ratio will I get?
The current output is an MP4 lasting 15 seconds in 16:9, with 480p / 720p / 1080p quality options. Check the current credit quote before generating.
Does this video include music or sound?
Yes. The finished video uses this template’s original soundtrack, including any music, vocals or scene sounds present in that track. The new subject does not record a separate singing voice.
What if the result looks wrong or generation fails?
Check the status in My Videos first. A technical failure returns deducted credits automatically; a completed result you dislike is a different case.See troubleshooting ↓View refund policy ↗