Product shots that ship the set.
One product photo in, a finished ad set out: AI-generated scenes that stay on brand, every channel size, captions included. Rerun it for the next SKU tomorrow.
One packshot. A whole set.
The product is locked; only the world around it changes. Every placement comes out sized for its channel.
- Product photo
- Brand kit
- Scenes ×N
- Resize
- Copy
- Ship
Story · 9:16
Post · 4:5
Banner · 16:9Done. Change the input and run it again.
Why it holds up
Your palette in every scene
The brand kit drives backgrounds, props and tone, so the summer drop and the winter drop still look like the same store.
Every channel, one run
Square, story, banner: the pipeline resizes and renames per channel, so a campaign lands as a set, not a folder of crops to make.
One subscription, all models
Swap image models per scene, photoreal here, illustrated there, without buying another tool. Costs show before you run.
Build it once. Run it again.
The workflow behind this page, step by step. Every step is a node you can open, change and rerun.
- 1Drop the product in
Start from the photo you already have.
Upload a product shot. The pipeline lifts it into generated scenes without losing the product.
No studio day, no white-cyc rental, no waiting on reshoots for a colorway.
Productspring-tote.jpg · 1 of 4 colorways
- 2Scenes, on brand
Generate the scenes your brand would shoot.
Image nodes compose the product into scenes steered by your kit: palette, mood, propping.
Compare three models side by side on the canvas and keep the best; the wiring doesn't change.
Scene directionmorning light · linen · quiet luxury
- 3Ship the set
Sized, captioned, named, done.
Every output lands cut for the channel with copy in your voice, a campaign ready to post.
Next SKU? Swap the photo and rerun. Only the changed steps recompute.
- Set
- hero 4:5 · story 9:16 · banner 16:9
- Copy
- captions in brand voice
- Named
- spring-tote · per channel
What you can make.
Starting points for product ads. Each one is a workflow you can open, change and run again.
- 01
Seasonal scene sets
The same product on a summer terrace, in a snowy cabin and on a studio sweep, one run per season.
- 02
Marketplace image stacks
A clean packshot plus lifestyle and detail shots for your Shopify, Amazon and Etsy listings.
- 03
Launch teasers
Short motion clips made from one still, for a drop countdown or a new-arrival post.
- 04
Colorway variants
A new backdrop and props for each colorway, with the product photo as the input every time.
- 05
Copy beside every image
Headlines and primary text written in your brand voice for each scene in the set.
- 06
Paid social sets
Story, feed and banner sizes from the same run, ready to upload.
The next SKU is a rerun.
Upload one product photo, wire it to your brand kit, and watch the set land sized and captioned, on the free tier, with the cost visible before each run.
With the rest of Orisu.
The workflow is one part. These are the other parts teams use with it.
Brain →Brain remembers your product claims and the words you never use, so scenes and copy stay accurate for every SKU.
Feed →Run the same ad set down your whole catalog from a CSV or Shopify, one row per product.
App Mode →Hand the workflow to merchandising as a form: upload a photo, press run.
API and MCP →Trigger the same workflow from your own code, or from Claude and ChatGPT, and get the files back.
Good to know.
Will the product look the same in every scene?
Your product photo is the input to every scene, and the brand kit's reference images go to image models as references. Check each output before it ships and rerun any that drift.
Can I do this for my whole catalog?
Yes. Mount the workflow as a column in Feed and run it over every product row from a CSV or Shopify import.
Which image models can I use?
Pick one per node from the catalog, for example FLUX, GPT Image, Nano Banana or Seedream, and swap it later without rewiring.
Do I need new photography for every campaign?
No. One decent product shot is enough. The pipeline composes it into new scenes, seasons and moods; the photo is the anchor, the scenes are generated around it.
Will the product stay accurate in generated scenes?
The scenes are built around your real product photo, and every node's output is reviewable on the canvas before anything ships. You approve the set, not a surprise.
Can it produce every ad size my channels need?
Yes. Resize nodes cut the set per channel (square, story, banner) and name the files per format, so a campaign exports as a ready-to-post set instead of a to-do list of crops.
Do I have to build this workflow myself?
No. Start from a template, or describe what you want and Orisu drafts the workflow for you. You can also build it step by step.
What does it cost to run?
Every node shows its credit cost on the canvas, and a run shows its total before you press it. The free plan gives you 100 credits a month with no credit card.
Can my team use it without learning the canvas?
Yes. App Mode turns the workflow into a simple form: inputs on top, a run button, results below.
Can I change models later?
Yes. Models sit behind the same ports, so you can swap one without rewiring anything. All of them are on one subscription.
Every SKU, one run.
Start free with your own product photo. The brand kit and the pipeline take it from there.