AI makers · 8 min read ·

Product Mockup Video Generator: Turn a Product Shot Into a Short Clip

A product mockup video generator turns one still of your product into a short moving clip, such as a slow push-in, a small turn or steam rising from a mug. In Toybox, make the still in Product Mockup, then give it to Video Creator as the start frame with a line describing the motion. Clips are 4, 6 or 8 seconds long and need a Pro plan or higher.

A product mockup video generator takes a still photo of your product and animates it into a short clip. In Toybox AI, the still comes from Product Mockup or from your own camera, and Video Creator, which is powered by Google Veo 3.1, turns it into a 4, 6 or 8 second MP4 from that start frame plus a written description of the motion. This page covers which product shots animate well, motion prompts to copy, video specs for Etsy, Shopify, Amazon and Pinterest, and what can go wrong with labels and small text.

What you can make with a product mockup video generator

A product mockup video works best when one thing moves and the product stays put. These are the shots that suit a still-to-video tool:

  • A slow push-in. The camera drifts toward a candle on a nightstand or a serum on a bathroom shelf and ends close on the product.
  • A small turn. The product rotates a few degrees on a turntable, enough to show depth without showing a side the photo never captured.
  • Ambient motion around the product. Steam rising from a mug, condensation running down a cold can, a flame flickering, leaves moving outside a window.
  • Light moving across a scene. Window light sliding across a tabletop, as if an afternoon passes.
  • Fabric in a breeze. A scarf, a tote bag strap or a curtain behind a product moving slightly.
  • A hand reaching in. A hand lifts the product off a table. The hand is invented, so watch the fingers and the label.
  • A start-to-end change. Add an end frame and the clip travels from one photo to the other, such as a closed gift box to an open one.
  • Vertical clips for social. Reels, TikTok and Pinterest, made in the Vertical 9:16 format (labeled "TikTok, Reels" in Video Creator).

A slow push-in, written for the "Describe your video" box in Video Creator, with your product photo as the start frame:

Slow dolly shot pushing in toward the candle on the wooden nightstand, eye-level, ending in a close-up of the jar. The candle, jar and label stay still and unchanged the whole time. Warm lamp light, a softly blurred bedroom behind, calm evening mood.

A small turn that doesn't reveal the back:

The sneaker rotates slowly about 20 degrees to the right on a round white turntable, then stops. The camera stays fixed at shoe height. Soft, even studio light, clean light gray backdrop, no other movement in the scene.

Motion around a still product:

Thin wisps of steam rise from the coffee mug and drift to the left. The mug stays completely still on the kitchen counter. Morning sunlight from a window on the left, shallow focus, the background softly out of focus, quiet and cozy.

Where product mockup videos can go

Each platform takes different clip lengths and shapes, so check the specs before you make the clip. As of September 2026:

Platform Length File and size Notes for AI clips
Etsy listings 3 to 15 seconds MP4, MOV and other formats, up to 100 MB Two videos per listing at most; audio is removed on upload; Etsy asks for a 2:1 or 1:2 ratio; 500 px minimum, at least 1080 px ideal
Shopify product pages Up to 10 minutes MP4, MOV or WebM, up to 1 GB and 4K Your theme has to support product videos
Amazon detail pages 1 to 12 minutes MOV or MP4, up to 1080p and 5 GB 16:9 or 9:16; the seller account needs more than three months of activity before it can upload
Pinterest video ads 4 seconds to 15 minutes MP4, MOV or M4V, up to 2 GB Pinterest recommends square or vertical video, and 6 to 15 seconds for video ads

The 4, 6 and 8 second clips fit Etsy's and Pinterest's lengths as they come. Etsy's 2:1 and 1:2 are a little wider and taller than 16:9 and 9:16, so preview the clip in the listing editor before you publish. For Amazon, cut several clips together into a video of at least a minute in a video editor. Amazon's video guide lists showing the product in use and demonstrating size and scale among the content it allows, so mix AI clips with real footage of those. The guide to Etsy mockups covers the rest of an Etsy image set.

Tips for better product mockup videos

  • Match the frame to the video shape. Toybox doesn't crop your start frame or resize it. To know what you'll get, make the still in the clip's own shape: Story 9:16 in Product Mockup for a Vertical video, Wide 16:9 for a Wide one.
  • Move one thing. One camera move or one moving element per clip. Stack a push-in, a turn and a hand in one clip, and you have three moving parts to check for label and shape changes instead of one.
  • Name the camera move. Google's Veo prompt guide lists the parts of a video prompt: subject, action, style, camera positioning and motion, composition, focus and lens effects, and ambiance. Words like dolly shot, eye-level, top-down shot, close-up and shallow focus come from that guide.
  • Say what stays still. Write that the product, the label and the packaging stay unchanged, and keep motion around the product rather than in it.
  • Use "Things to avoid". In Video Creator, add lines such as "label text changing, extra products appearing, hands" under "More options".
  • Control the ending. An end frame sets where the clip lands. A second photo taken on the same set, a few degrees around, shares the start frame's light and background, which a separate AI image may not.
  • Start sharp. The clip opens on your still, so any blur or noise in it is on screen from the first frame. Use your sharpest image.

A light change across a flat lay, with no product motion at all:

Top-down shot of the tote bag lying on a light wooden floor. A soft patch of window sunlight slowly slides across the floor from left to right, and its shadow shifts with it. The bag, its print and the props do not move.

A 3D product mockup video from one photo

A 3D product mockup video usually means a full 360-degree spin of a 3D model of the product. A clip from an AI product mockup video generator starts from one photo, not a 3D model: when the product turns, the AI has to make up the sides it never saw, including the back label. Keep turns to roughly 15 to 30 degrees, so most of what the viewer sees came from your photo.

  • For a short turn, use one photo and keep the rotation small.
  • For a controlled turn, photograph the front and a side view on the same set, and use them as the start and end frames.
  • For an exact 360-degree spin, film the real product on a turntable with your phone, or render it from a 3D model file.
  • For a spin the shopper controls, Shopify product pages can show the 3D model itself (a GLB or USDZ file up to 500 MB) on themes that support 3D models.

Limits to know

  • Labels and small text can shift. Toybox doesn't guarantee that a label or printed design stays sharp and unchanged while the clip moves. Keep motion short and subtle, pause on the label before you publish, and include a still close-up of the label among the listing photos.
  • Sound comes only from the prompt. Video Creator and Lite clips come with sound, but there's no volume or music setting, so describe the sound you want next to the motion. To use your own music or narration, lay it over the clip in an editing app.
  • Video Creator makes 720p clips. Etsy calls 1080 px or more ideal. Video Creator Lite, which uses Veo 3.1 Lite, has a 1080p option, locked to 8 seconds.
  • Exact print placement needs a template tool. Product Mockup places the product in your photo into a scene; it doesn't print a flat design onto a blank mug or shirt. For a moving mockup with your artwork at exact proportions, a template-based video mockup tool fits better.

The manual way: film a turntable clip

A real turntable clip is the free option and shows every side honestly.

  1. Set the product on a lazy Susan or a cake stand on a white sweep, next to a window.
  2. Fix the phone in place, on a tripod or wedged between heavy books, level with the product.
  3. Tap the product to focus and, if your camera app offers it, lock focus and exposure, so the brightness doesn't shift as it turns.
  4. Record while you turn the stand slowly by hand, one full rotation in about 10 seconds.
  5. Trim the clip to the smoothest 3 to 15 seconds for Etsy.

How to animate a product still in Video Creator

  1. Make the still. Open Product Mockup, upload your product photo, pick a Scene, set the Size to Story 9:16 or Wide 16:9, press "Create mockup" and download the PNG. You can also use a photo you took yourself.
  2. Go to Video Creator, which needs a Pro plan or higher.
  3. Tap "Start from a photo" and add the still; it becomes the Start frame. An End frame is optional and decides the final shot, but it also makes the clip 8 seconds long.
  4. In "Describe your video" (up to 2,000 characters), describe one motion, the camera move and what stays still, like the prompts above.
  5. Choose the Format (Wide 16:9 or Vertical 9:16, matching the still) and the Length (4, 6 or 8 sec).
  6. Optional: open "More options" and list anything to leave out in "Things to avoid".
  7. Press "Create video". A clip takes a few minutes. Play it full screen, stop on the label and the product's edges, then download the MP4.

Video Creator currently costs 350 credits per clip, whatever the length or shape, about $3.50 at top-up prices. Video Creator Lite currently costs 180 credits at 720p or 220 at 1080p, and Product Mockup 75 credits per still. If a clip fails, the credits go back automatically (see current prices). Animating other kinds of photos is covered in turning any photo into video, and to build a full ad from several clips and copy, see the AI commercial generator page.

Frequently asked questions

Is there a free product mockup video generator?

Toybox's video tools aren't free. Both of them, Video Creator and Video Creator Lite, require Pro or a higher plan, currently from $9.99 a month for 1,000 credits, and a clip currently costs 350 credits in Video Creator or 180 to 220 in Lite. The free route is filming the real product on your phone, turning slowly on a lazy Susan in window light.

Do the product videos have sound?

Yes. Clips from Video Creator and Video Creator Lite come with sound. There's no separate setting for it, so describe what you want to hear, such as "soft acoustic music, no voices". Etsy removes audio from listing videos on upload anyway. For a Shopify or Amazon video with your own voiceover or music, add it in a video editor, and use music you have the rights to, since Amazon's video guide bars unauthorized music.

What file do I get from Video Creator?

One MP4 clip per run, 4, 6 or 8 seconds long, in Wide 16:9 or Vertical 9:16. Video Creator outputs 720p. Lite adds a 1080p choice, and a 1080p clip always runs 8 seconds. Download the clip or keep it in your gallery; unsaved results stay available for 24 hours.

Can I use AI product videos commercially?

Toybox's Terms of Service say you own the rights to the outputs you generate (images, text, video, and code), subject to the Terms. You're responsible for how you use them, so check copyright, trademark and platform rules first. If a clip shows a photorealistic person made by AI, Amazon asks you to tag the file with contains-synthetic-performer before uploading.

What is the difference between an AI mockup generator video and a template video mockup?

A template video mockup drops your flat artwork into a ready-made moving scene, such as a spinning mug or a model in a t-shirt, with exact placement. An AI mockup generator video animates a photo you already have, so the motion is new each time and small details can change. Use templates when print placement has to be exact.

Sources

Make it with AI Video Creator

Keep reading