Preview with sound

Reference assets

2 images
  • A presenter on front steps holds up one white low-top lace-up sneaker to the camera1
  • Reference product photo — A plain phone photo of a pair of white sneakers2
Format
9:16
Length
30s

These are the assets and settings this result used. The example video is the result, not an input.

Create AI UGC Videos from Your Product Photos

White Sneaker · Front Steps Ad

Format
9:16
Length
30s

Opens the workspace with this template already selected. You can change the product, format and length.

Prompt

Wan 3.0; 30s; 9:16; sound on; two-image reference generation, neither image used as a forced first frame. A natural-daylight, front-door outfit e-commerce short film that preserves the real details of the upper, stitching, laces and sole, with relaxed, natural movement. Show the look of this pair of white low-top lace-up sneakers, the lace-up structure, and everyday wear-and-walk use. The reasons to buy center on the clean white look and how it pairs with jeans; do not add unconfirmed selling points such as genuine leather, waterproofing, slip resistance, cushioning, or all-day comfort. Reference images: image 1 locks this pair's silhouette, laces, tongue, stitching and white sole; materials render only as their visible surfaces, with no leather-type inference. Image 2 locks the adult woman's face, her brown updo, the cream knit sweater, the light-blue jeans and the front-step setting. Identity and outfit stay consistent across shots; the shoe model is decided by image 1. Scene: the same front steps in soft natural daylight on dry, even ground. The presenter starts seated and settled, the right shoe already on her right foot and the left foot in a sock resting on the step; the left shoe is held in both hands with its laces loosened. There is exactly one pair of shoes in the whole piece. Shot 1 [0-6s] 50mm medium shot; her mouth and the left shoe are in frame together. She shows the side of the shoe naturally and says: "A simple white sneaker pairs easily with a casual denim outfit." Shot 2 [6-12s] Hard cut to a locked 85mm close-up. Her left hand supports the sole and her right hand steadies the heel as the same left shoe rotates at a small angle to show the upper, stitching and lace structure; both hands keep supporting it. The shoe is never bent or squeezed, and there is no dialogue. Shot 3 [12-18s] Hard cut back to the 50mm medium shot; putting on the left shoe is explicitly omitted through an edit. The shot begins with both shoes correctly worn and laced; she sits settled, her mouth visible, and says: "The lace-up design lets you adjust the fit before heading out." Shot 4 [18-24s] Hard cut to a low, locked close-up that cuts in at the moment she is already standing, omitting the process of getting up. She takes two small natural steps on the flat ground in front of the door, heel and forefoot landing in natural gait order, the upper flexing gently at the toe joints; the camera stays in place and the walk finishes inside the frame. No dialogue. Shot 5 [24-30s] Hard cut to a 50mm standing medium shot; she has come to rest by the door, both feet still, facing the camera as she says: "Choose them for a clean, simple look with your everyday outfits." Sound: a natural English on-camera voice, lip-synced, speaking only when the mouth is visible. Close-ups carry no dialogue; keep light clothing sounds, natural contact sounds while handling the shoe, and two footstep landings. No background music. Limits: the right and left shoes never swap and never multiply into a third shoe; laces, tongue and sole stay continuous. Putting on the shoes and standing up are bridged through explicit edit omissions — no feet morphing into uppers, no shoes snapping onto feet. Steps never slide or float, and the sole never sinks through the ground. No running, jumping, or slip tests that imply unconfirmed performance. No added text, captions, auto-subtitles, branding, or watermarks.

The workspace opens with this prompt so you can change the shot, product, format and length before you generate.