Start from a still you have approved
Make a try-on, model swap or model background change first, or upload your own photo, and pick the version you would publish as a picture.
Fashion model videoComing soon
Choose a model photo you are happy with, pick how the model moves, and get a short clip that starts from that exact frame.
Open the workspaceThis tool is in private testing and is not open to all accounts yet. The page describes how it will work; the workspace shows which tools your account can use today.
How it works
The TrendRemix fashion model video tool animates one confirmed model photo, such as a virtual try-on result. The photo becomes the first frame, so the person, outfit and setting you approved carry into the motion. You pick one of five motions: a slow turn showing the front, side and back, a walk toward the camera, a few relaxed pose changes, a push-in to fabric and details, or a gentle breeze moving clothing and hair. Clips are 5 or 10 seconds in 9:16, 3:4, 1:1 or 16:9, with up to 400 characters of optional notes. Results are saved as MP4 files in your asset library.
Make a try-on, model swap or model background change first, or upload your own photo, and pick the version you would publish as a picture.
Match the motion to the garment: a turn for fit, a walk for drape, a push-in for texture. Set the length and ratio and check the credit quote before you submit.
The clip is generated in the background. Watch it in full, then download it or keep it in your asset library for an edit.
From a full turn that reveals the back of a garment to a slow push-in on fabric and stitching, each motion is designed to show what a still cannot.
Because your photo is the first frame, the model, outfit and background you chose are the starting point rather than being reinvented.
The clip is generated without captions, logos or watermarks, leaving room for your own titles and price overlays.
Sits in the same model photography workspace as virtual try-on, model swap and model background, so a result can become a video in one more step.
| Input | One image, JPG, PNG or WebP, up to 20 MB |
|---|---|
| Motions | Turn around, walk toward camera, change poses, push in to details, gentle breeze |
| Length | 5 or 10 seconds |
| Formats | 9:16, 3:4, 1:1, 16:9 |
| Notes | Optional, up to 400 characters |
| Output | 720p MP4, saved to your asset library |
| Cost | Credits by length, shown before you submit |
Only with the model's consent and your right to use the image. The video service may refuse photos of real people; if it does, the task fails and its credits are returned.
The tool only sees what your photo shows, so any side the camera never saw is generated. For an accurate back, start from a photo that shows it, or choose a motion that stays facing the camera.
You choose one of the five motions and can steer it with up to 400 characters of notes. For an open prompt, use the AI video generator with the photo as the start frame.
No. Captions, logos and watermarks are deliberately left out so you can add accurate ones in your editor.
5 or 10 seconds. For a longer piece, join several clips in an editor, or use video remix for an assembled 15, 30 or 45 second video.
Every result lands in your asset library, ready for the next tool.