01
Step 1
Select the reference asset that shows the product most completely under neutral lighting as the lead, list the secondary angles with their known colour casts, and record the exact output dimensions and placement the image must serve.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Generate a product image brief from reference assets
The merchant holds several reference assets of uneven quality and needs one image built for a specific placement. In this case, the immediate task is to generate a product image brief from reference assets. The workflow should produce a brief or generated image pinning shape, colour, markings and composition, checked against the chosen reference.
Topic
Product Image Generation
Target keyword
shopify product image generator
Copyable AI prompt
A prompt you can drop directly into Spark
First replace every [bracketed] placeholder with real store scope and constraints, then add any actual records or data you have, and paste it into your preferred AI assistant or Spark agent. Spark will follow this page's workflow to produce structured output and verification steps.
ai-prompt.txt
Act as a Shopify operations specialist.
Help me generate a product image brief from reference assets.
My store context is [describe the business, products and target audience].
My scope is [specify the affected products, pages, customers or reporting period]. Use these inputs: [the lead reference asset in neutral lighting, secondary angle references with known colour casts, and the required output dimensions and placement]. Write a brief that pins shape, colour, markings and composition to the lead reference, states which details come from which source, and names the elements that must not drift, so generation has no room to invent product features.
Return the brief or a generated image for the specified task.
Show the relevant evidence or before-and-after examples and explain how I can verify the result.
If essential data is missing, ask for it and mark unsupported conclusions as unknown.
Do not invent metrics, product claims or customer facts.
For any publication, message, account or store change, use only connected tools within my explicitly authorized scope and report success only after verification; otherwise provide the draft or proposed steps.How to solve
A recommended resolution workflow
Split the work into input, judgment, and deliverable phases. Verify each step's output before moving to the next.
02
Step 2
Write a brief that pins shape, colour, markings and composition to the lead reference, states which details come from which source, and names the elements that must not drift, so generation has no room to invent product features.
03
Step 3
Deliver the brief or the generated image with an item-by-item comparison against the lead reference covering shape, colour and markings, record every mismatch, and pair the output with verified photography rather than letting it stand as the product's only visual.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Which reference leads when assets disagree?
The one shot under neutral lighting with the product most fully visible; when a secondary angle contradicts it on colour or markings, the discrepancy is recorded in the brief and resolved against the verified product record, never averaged into the image.
What must the brief pin versus leave open?
Shape, colour, identifying markings and composition are pinned to the reference because drift there misrepresents the item; background styling and framing may stay open within the placement's size rules, as long as nothing implies a feature the product lacks.
How is a generated image verified before use?
By walking the same checklist used to write the brief — shape, colour, markings, composition — against the lead reference and logging each mismatch; the image is then paired with verified photography until the merchant accepts generated visuals as the sole representation.
Related scenarios
Continue with adjacent or same-topic scenarios
Start with scenarios under the same topic, then expand into cross-topic matches suggested by similarity.
Next step
Want these AI scenarios embedded directly into daily operations?
Ciwi Spark builds Shopify-native AI tools and agents around the workflows merchants actually run: research, ads, translation, and customer support. Stop rewriting the same prompts by hand.