01
Step 1
List every product in the batch with its reference image, the shared brand style rules covering lighting, angle and background, and the output sizes required, and mark any product whose reference is missing or unusable.
Back to topic
Spark playbook scenarios · Spark: AI Store Assistant
Prepare a batch of product-image generation briefs
A whole range needs new visuals at once, and briefing products one by one has produced results that do not match. In this case, the immediate task is to prepare a batch of product-image generation briefs. The workflow should produce one brief per product that fixes scene, composition and the details to preserve, so the batch reads as a single set.
Topic
Product Image Generation
Target keyword
bulk 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 prepare a batch of product-image generation briefs.
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 product list with reference images, shared brand style rules for lighting, angle and background, required output sizes, and the markers for products lacking usable references]. Write one brief per product from a shared template that fixes scene, composition and the details each product must preserve, carrying that product's own reference specifics so no item inherits another's attributes, and hold reference-less products out of the batch.
Return the batch of briefs or generated files 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 one brief per product from a shared template that fixes scene, composition and the details each product must preserve, carrying that product's own reference specifics so no item inherits another's attributes, and hold reference-less products out of the batch.
03
Step 3
Deliver the batch with a coverage check that brief count equals listed products minus held-out items, compare each output against its own reference and against siblings for lighting, angle and background consistency, and log every mismatch and held-out product with its reason.
FAQ
Common questions when running this scenario
Cover decision rules, frequent misunderstandings, and required inputs so the team aligns on prerequisites before execution.
Why one brief per product instead of one for all?
A shared template keeps the set consistent, but each brief must carry that product's own reference details — colour, markings, preserved features — because a single blanket brief lets one product's attributes bleed into another's image, and the mismatch usually only surfaces after generation.
How is batch consistency verified?
Each output is checked twice: against its own reference for product accuracy, and against sibling outputs for lighting, angle and background treatment; both checks are logged per image so a single off-style frame is traced to its brief rather than regenerating the whole batch.
What happens to products without references?
They are held out with the reason recorded and a reference requested from the merchant; generating without one risks an image that does not match stock, and inserting it later means re-checking the whole set's consistency anyway.
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.