A wide 16:9 follow along a sunny old-town street. Someone bumps your shoulder. Gold-frame sunglasses and a pink-label iced coffee fly at the camera in slow motion, pass through the lenses, and end on the cup. About 10 seconds. The song is added after.
No prompt to write: Add your photos and tap once
Create your ownReady in a few minutes · From 152 credits
Drink Fly Bump AI is the landscape street clip where the accessories leave the walker and hit the lens. It stays wide 16:9 on every tab. Human uses the sunglasses and the iced coffee already in the clip. Your shades + drink swaps those two props for photos you upload. Pet puts one animal in the walker’s place.
Open Drink Fly Bump AI and generate. You do not write a prompt. This is not a vertical 9:16 template.
Also called drink fly bump, sunglasses fly into camera AI, drink bump trend
Wide 16:9, about 10 seconds. Street follow, shoulder bump, then the sunglasses and the drink in slow motion. The sample can show a watermark. Your download has no watermark.
The frame stays landscape. The sunglasses and the cup come toward the lens, then the label fills the shot.
The price on Generate is the price for that tab.
Human keeps the clip’s sunglasses and drink. Your shades + drink uses two extra photos. Pet is one animal. Every tab is wide 16:9.
You first. If you chose shades and a drink, the sunglasses photo is second and the cup is third.
About 10 seconds. The song is added after the silent shot. Your download has no watermark.
Use your own photo. If you upload sunglasses or a drink, use objects you own.
A low camera follows a walker on a sunny old-town street. A passer-by bumps a shoulder. Sunglasses and an iced drink leave the walker and fly at the lens.
The fly-in needs the landscape frame. A vertical crop cuts off the sunglasses and the cup as they reach the camera, so this page stays 16:9.
You do not write a prompt. Each tab names who is in the clip and how long it runs.
Replace only the walker with the adult in [Image 1]. Keep the face and hair from [Image 1]. Keep the low follow along the sunny old-town street, the shoulder bump, the slow motion as the gold-frame sunglasses and the pink-label iced coffee fly into the lens, the pass through the lenses, and the cup-label close-up. Those props stay the ones in [Video 1]. Wide 16:9 from the first frame to the last. Do not crop to a vertical frame. Edit [Video 1] in place. Use each uploaded image ONLY as the identity reference for its assigned role. Preserve the complete performance in [Video 1], including frame order, camera, lighting, location and timing. Do not restage the clip or create new shots. Do not add text, logos or a watermark. Produce a silent video; the original reference soundtrack is added separately. The reference video is about 10 seconds. Preserve its full action and timing without retiming, extending, adding or removing shots.
941 charactersReplace the walker with the adult in [Image 1]. Replace the sunglasses that fly into the lens with the pair in [Image 2]. Replace the drink that flies in with the cup in [Image 3]. Keep the low street follow, the shoulder bump, the slow motion into the lens, the pass through the lenses and the label close-up. Wide 16:9 from the first frame to the last. Do not crop to a vertical frame. Edit [Video 1] in place. Use each uploaded image ONLY as the identity reference for its assigned role. Preserve the complete performance in [Video 1], including frame order, camera, lighting, location and timing. Do not restage the clip or create new shots. Do not add text, logos or a watermark. Produce a silent video; the original reference soundtrack is added separately. The reference video is about 10 seconds. Preserve its full action and timing without retiming, extending, adding or removing shots.
896 charactersReplace the walker with the pet in [Image 1]. The pet keeps its species, face, ears, fur and markings, and stays upright on its hind legs. Keep the clip’s outfit on the walker and the gold-frame sunglasses and iced coffee from [Video 1]. Keep the low street follow, the shoulder bump and the slow-motion fly-in. Wide 16:9 from the first frame to the last. Do not crop to a vertical frame. Edit [Video 1] in place. Use each uploaded image ONLY as the identity reference for its assigned role. Preserve the complete performance in [Video 1], including frame order, camera, lighting, location and timing. Do not restage the clip or create new shots. Do not add text, logos or a watermark. Produce a silent video; the original reference soundtrack is added separately. The reference video is about 10 seconds. Preserve its full action and timing without retiming, extending, adding or removing shots.
897 charactersYou pay in credits. The Generate button shows this price before you spend anything. These are the options on this page.
| Option | Model | What you get | Credits |
|---|---|---|---|
| Human | Wan 3.0 | 10 s · 480P · 16:9 | 152 |
| Your shades + drink | Wan 3.0 | 10 s · 480P · 16:9 | 152 |
| Pet | Wan 3.0 | 10 s · 480P · 16:9 | 152 |
One-time packs and plans are on the pricing page. A failed video gives its credits back.
The primary shot is a wide street frame, about 800 by 452. The sunglasses and the drink travel toward the lens across that width. Every option here, Human, Your shades + drink, and Pet, is generated 16:9 at 480P for about 10 seconds. Do not expect a 9:16 file from this template.
The middle tab takes three photos: your face, the sunglasses, and the cup. Shoot the objects on a plain background so the frames and the label are easy to see. Human and Pet keep the gold frames and the pink-label coffee from the reference.
It is a wide street clip, about 10 seconds, where sunglasses and a drink fly into the camera after a shoulder bump. Your photo is the walker.
Choose Human, Your shades + drink, or Pet, upload the photos, and press Generate. No prompt.
No. It spends credits. The price is on Generate. Sign in, add credits if you need them, then run it. A failed generation refunds the credits.
Yes. The shot is made silent, then the soundtrack from the reference is added.
Human and Pet need one. Your shades + drink needs three: you, the sunglasses, and the drink, in that order.
Wide 16:9 only, about 10 seconds, 480P. It is not a 9:16 Reel crop.
The sample on this page can show a watermark. Your download has no watermark.
You can upload it. Those apps are built for vertical video, so a wide clip will letterbox or crop in their editors. The file from this template stays 16:9.
No. Make it on this website, including in a phone browser, and download the MP4.
Yes. Pet is one animal, upright, in the same wide street shot, about 10 seconds. The sunglasses and the drink stay the ones from the clip.
“So 1, 2, 3, go.” A sprint down a bright hall, a slip through a white door that is already closing, a knee slide, and a laugh from the other side. The door does not hit anyone.
Read moreTemplateA pink flamingo float on a rooftop infinity pool. Dubai, the default, drifts toward the edge for about 11 seconds and a hand pushes it back. Singapore is already tipped, about 10 seconds, with no hand. You, a couple, or your pet.
Read moreTemplateOne photo becomes the upright Stateside routine in a plain grey studio: bounce, side step, kick, hands on the head, hip pop, and a high arm finish. Human is about 14 seconds. Pet is about 15 seconds. The song is added after the silent dance.
Read moreTemplateA quiet restaurant in black and white. You sit the round table with a cold stare, bodyguards in sunglasses beside you, then walk slowly toward the camera. About 10 seconds. The dark beat from the reference is added after. No guns.
Read more16:9, about 10 seconds. Sunglasses and a drink, into the lens.
No watermark. A failed video gives its credits back. Secure checkout by Stripe.
