ItemlumeAI models / PRODUCTION GUIDE
Can one Itemlume product request use two saved AI model references?
The current Itemlume product-image request selects one saved model reference. A campaign can use different references in separate images, but that does not provide two independently controlled identity inputs in one scene. Decide whether you need a coordinated image pair or a genuine joint interaction before choosing the production method.
Separate a two-person cast from a two-person request
Consider an illustrative backpack campaign with two fictional adult characters, Rowan and Tessa. The team wants both to appear reliably across the campaign. A set of separate portraits and product scenes can serve that casting plan. A single picture of them exchanging the backpack introduces another requirement: two controlled identities and a coherent joint interaction within the same generated composition.
Write which result is actually needed before selecting inputs. If the campaign simply needs both characters represented, a coordinated pair may be sufficient. If the story depends on their interaction, two independent portraits cannot establish the hands, ownership and contact relationships of that joint scene. Do not describe the simpler output as though it records an exchange that never appears.
Check the selector rather than counting uploaded photos
In Product images or Virtual try-on, the model picker selects one official or saved model for the request. The product or garment uploads provide evidence about the sale item. Adding another person’s photograph to those slots does not create a second designated identity selector or a rule assigning one reference to each figure.
Google documents subject-reference identifiers. Those controls belong to that documented workflow; they do not change Itemlume’s input options. Use the reference-source guide to select an appropriate identity source, but keep the number of independently controlled identities separate from the number of reference images visible in an upload area.
Choose the output that matches the story
| Campaign need | Workable planning choice | Limit to acknowledge |
|---|---|---|
| Both characters represented | Separate reviewed product scenes | They are not interacting in one image |
| Two panels on one graphic | External layout of approved separate assets | Do not imply a continuous shared scene |
| A specific joint exchange | Suitable real production or separately verified workflow | Current single-reference input does not establish both identities |
| One primary character | One selected reference in Itemlume | Additional generated figures have no second identity binding |
For Rowan and Tessa, a two-panel launch graphic can keep both people distinct while showing the same verified backpack edition. Approve each scene separately, then assemble the layout externally. Carry shared lighting and visual direction as editorial choices, while checking the product in each output. Matching backgrounds should not make the panels appear to record the same physical moment if that is not their intended story.
If the exchange itself matters, reconsider the production method before spending on repeated unsupported attempts. A separately designed composite may be appropriate for an openly graphic treatment, but realistic interaction needs its own contact and anatomy review. Neither solution follows automatically from saving two references. Choose the method around what the viewer should understand, rather than the desire to fill every available upload slot.
Pilot each supported identity with the actual product
Select Rowan’s approved reference and create a simple product scene, then repeat the process separately for Tessa. Inspect the face, hair and visible identity cues as well as the backpack’s seams, straps and count. A correct face does not approve a distorted product, and a correct backpack does not establish that the generated person follows the chosen reference accurately.
Use the contact-sheet review guide to compare each character’s own outputs. Keep those series separate so an accidental blend of their features is not approved as creative variation. Itemlume’s portrait creation describes one fictional adult; it does not produce a controlled two-character cast merely because two names are written into an appearance description.
Handoff the identity decision with the approved files
Give the external editor the separate approved images, character names used for organization, product edition and intended panel relationship. State whether the layout is a coordinated campaign comparison or a depiction of interaction. Avoid adding captions that invent a real biography, customer experience or testimonial for either fictional character. Their visual consistency and public role are separate review questions.
If a generated image happens to contain two plausible figures, do not treat that as evidence of two saved identities being controlled. Compare each figure to its authorized source and reconsider whether the unsupported second person belongs in the final asset. This example documents the current input boundary and production choice; it does not promise perfect identity retention, multiple-identity controls or a tested joint-scene result.
Sources and further reading
Sources for this page were checked on . Platform rules can change; verify the current source before publishing. Prompt examples and workflow recommendations are Itemlume editorial guidance, not independently measured results.
Frequently asked questions
Can I select Rowan and Tessa together in the current model picker?
The current product-image request has one selected model reference. Use separate requests for separately controlled scenes, or choose another appropriately verified production method for a joint scene.
Does uploading Tessa as a product photo add a second identity slot?
No designated second identity control is created that way. Keep product uploads focused on sale-item evidence and use the model picker for its supported role.
If the output contains two people, does that prove both references were followed?
No. The presence of two figures does not establish per-person identity control. Review the actual figures and the scene’s intended meaning before using it.
BUILD FROM A PRODUCT YOU KNOW
Put this workflow into practice with your own product.
Explore the relevant tool first. AI copy and concept planning are free after sign-in. Image and video generation require available credits and the applicable account access.
Open AI models Check pricing and credits