Starting from the photos you already have
Turn product photos into video
The photos on your product page are the input. Not a shoot, not a 3D model, not a studio booking — the same JPEG a customer already sees. What you get back depends more on that photograph than on anything you choose afterwards, so this page is about the photo.
One subscription, every mode, cancel in two clicks. The clips below were rendered by this tool from real storefront photographs.
The modes for this
2 of them apply here
Product Showcase
0 CR · 6sA slow camera move across a lit set, built from your own photo.
Built from your photo, so the product is never redrawn and no word on your label can change. The camera pushes in and drifts while a single key light travels around the set — the product itself is never stretched, mirrored or re-lettered, because one photograph holds one side of an object and this mode will not invent the other one.
Cinematic Commercial
3 CR · 5sYour product as the star of a premium commercial.
An AI model animates your photos. It looks like a commercial and it can quietly change small text, logo detail and edge proportions — always check the result before you publish it. Adding a second and third angle is the best defence against that.
Before you spend a credit
What makes a photo work here
One product, on a plain and even background. A white sweep is ideal and a flat colour is fine. The background is separated by filling inward from the edges of the frame, so there has to be a background for that to find — a busy room or a model holding the product gives it nothing to work with.
Big enough and not a panorama. The studio checks the dimensions and the shape of the file before anything is sent anywhere, and tells you what is wrong instead of rendering something with a torn edge.
More angles beat a better angle, for the AI modes. Front, back and a three-quarter view turn invention into interpolation: the model stops imagining the side it cannot see and looks it up instead.
A screenshot of your own product page is usually good enough to find out. If it is not, the uploader says so before you spend anything.
Output shapes
Render it in the shape you are going to post
The shape is an instruction to the renderer rather than a crop afterwards, so a vertical clip is composed vertically instead of being a landscape one with the sides cut off. Best first for this job:
- 9:16
Vertical · 1080×1920 · TikTok, Reels, Shorts
- 1:1
Square · 1080×1080 · Feed ads, Shopify grid
- 16:9
Landscape · 1920×1080 · Site hero, YouTube
The gallery
Finished clips, each beside the photo it was made from
Press one to play it; hold the button under it to see the original photograph. These are not reels we commissioned — they came out of this tool.
Bookshelf speaker
A matte cabinet beside a grille cloth — two very different surfaces, both lit by the same set rather than by a model's idea of a speaker.
Soda can
The hardest case for an AI video model and the easiest here: the artwork wraps the can, and an image-to-video model asked to move it would re-letter the whole thing.
Coffee bag
A soft pouch with small type down the front. Every word on the label is the merchant's own pixels, at every frame.
Supplement bottle
White bottle, white label, white backdrop. The cut works because it fills inward from the frame edge and stops at the bottle, instead of deleting every white pixel.
Roll-on applicator
Gloss black, which is why the set behind it is light: the renderer measures the product against the backdrop and refuses to leave a dark product on a dark one. Every line of the 8% complex panel is readable in every frame.
Oral care kit box
A box is the shape this mode suits best: flat faces and straight edges take a travelling key light the way the real thing would.
Every clip above is a Product Showcase render, made by this tool from the single public product photo behind it — hold any tile to see that photo. The shops those photos came from are not customers, have not seen this, and haven’t endorsed anything; they are here because using a real catalogue photo is the only honest way to show what this does to one. The AI modes have no published examples yet.
These are the shapes Product Showcase is good at: bottles, cans, boxes, bags and hard goods with a face worth reading. It films one photograph from a moving camera, so it never shows you a side the photograph didn’t contain — and the two things it is honestly worse at are flat-laid clothing, which has no edge for the light to catch, and products photographed against a busy background, which cut out badly. Try it on your own photo before you decide.
What this will not do
One photograph holds one side of an object, and nothing here pretends otherwise. The showcase mode never turns the product — it moves the camera and the key light around it instead, so what you photographed is what is on screen at every frame. If you need the reverse face on screen, photograph the reverse face.
Pricing
One plan, every mode
StoreFix Pro
$19 / month
20 credits a month for the modes that run on a video model. Product Showcase renders on your own device and takes nothing out of them. Cancel from the billing portal.
FAQ
Questions
How many photos should I send?
One is the common case and works. The generative modes will use several if you have them, and that is the single biggest improvement available to a result — it is the difference between a model inventing your packaging and copying it.
The studio tells you how many that mode will send and will not silently use fewer than it claims.
Can I use a photo with a model or a prop in it?
Not for the showcase mode. It has to find an edge between your product and its background, and a hand, a table full of props or a baked-in text overlay all become part of the cutout and travel with it as one rigid shape.
The AI modes are more forgiving of a busy photo and less faithful to it. Both facts are the same fact.
What kind of photo do I need?
One photo of one product on a plain, even background — the kind of shot that is already on your product page. A white studio backdrop is ideal, a flat colour is fine, and a photo with props, a model, text baked into it or a busy room is not: the backdrop is separated from the product by filling inward from the edges of the frame, and there has to be a backdrop for that to find.
You do not have to guess. The studio tells you how even the background was before it renders, and refuses rather than producing something with a torn edge.
Does my product actually rotate?
No. It does not rotate at all, and that is the point. Product Showcase is a camera move and a lighting move on a still product: the camera pushes in 6%, drifts 5% of the frame across, and rolls 0.9°, while a single key light orbits the set — so the lit side, the rim on the far edge and the direction the shadow falls all change together. Your photo is translated, scaled evenly and rolled. It is never stretched on one axis, never mirrored and never redrawn.
That sounds like less than a rotation and it looks like more, because the two versions that did claim to rotate were both visibly fake. The first mirrored your photo for the back half, so a bottle reading "JOINT HEALTH" came out "HTLAEH TNIOJ" for three seconds of every six. The second dropped the mirroring and squeezed the cutout to 31% of its width instead — which no real object does. A drinks can is a cylinder: its outline is the same rectangle however you turn it, so a squeezed can reads as wrong instantly even though nobody can say why.
If you need to see the back of your product, no software can get it from a photo of the front. Shoot the back and run it as a second clip.
You already have the photo.
Product Showcase turns it into a finished mp4 in about the length of the clip, on your own machine, with no queue to wait in.