What you say to the agent
No special syntax — just describe it like you would to a person.
What it does, step by step
- 1
The agent opens an Asset Builder card in the app for you to upload reference images of a character, product, prop, or location.
- 2
For a full cast at once (typical when starting a new workflow or cloning a template), it opens several cards in one go instead of looping one at a time.
- 3
Once saved, that asset is reusable by key across every scene in the workflow — no re-uploading per scene.
What it needs from you
- •A short key identifying the asset
- •A name for the character/product
- •What kind of asset it is
- •A description of the asset
What comes back
A saved, reusable asset (with reference images) bound to your workflow.
What it costs
Uploading reference assets doesn't use generation credits.
Under the hood
This is what the agent actually calls when you ask for it — real tools from its live surface, not marketing copy.
request_asset_uploadrequest_asset_batchcreate_workflow_assetupdate_workflow_assetlist_workflow_assetsOpen the Asset Builder UI on the client so the user can upload reference images for ONE asset. CALLING THIS TOOL *IS* HOW THE UPLOAD FORM APPEARS — there is no form unless you call it. If you only write text like 'please upload a photo' without calling this tool, NOTHING renders and the user is stuck. This is the ONLY way to collect references — never ask the user to paste URLs into chat and never describe the upload step in prose as a substitute for calling the tool. Call this once per character/product/etc., serially. Wait for the synthetic "✓ Saved <name>" confirmation message in chat before calling request_asset_upload for the next asset. The tool itself performs no database writes; it's a UI signal. The frontend renders an inline card prefilled with your suggestions, handles the upload + POST /workflow-assets call, and echoes the result back to chat. Pass exactly one of workflow_id (for video scene workflows) or slideshow_schedule_id (for recurring slideshow series with image-to-image generation).
See it done in a real workflow
Morning Matcha Routine
UGC-style wellness reel — a clean-girl creator walks through her actual morning matcha ritual, then cuts to a cozy animated hero shot of the finished iced latte.
TrendingNYC Street Interview
Photorealistic street-vlog interview — Riley works three different NYC corners at golden hour asking strangers one question: "What's the wildest thing you've ever done?" Three candid OTS/two-shot clips with locked character references, real handheld energy and native spoken dialogue. Vertical 9:16.
TrendingPrimo Protein vs Other Brand
Pixar-style 3D comparison ad — the confident PRIMO PROTEIN pouch faces off against the tired old rival brand's tub across 11 talking clips: pasture vs dusty pantry, herb garden vs toxic lab, clean American lab vs grimy factory, chocolate-milkshake CTA vs "wet sand." ~40s vertical reel with native character voices.
Or start from a one-tap template
Frequently asked questions
What do I actually say to the agent to set up reusable characters and products for a workflow?+
Just describe it in plain English — for example: "Set up an asset for my main character so I can reference her in every scene" The agent handles picking the right tool and model from there.
What does the agent need from me first?+
At minimum: A short key identifying the asset; A name for the character/product; What kind of asset it is; A description of the asset. Anything else it needs, it asks for before running.
What do I get back?+
A saved, reusable asset (with reference images) bound to your workflow.
Does this cost credits?+
Uploading reference assets doesn't use generation credits.
Is this one single action, or several?+
Behind the scenes the agent may call more than one tool to pull this off — but you only ever describe the outcome you want in one message.
You can also just ask for
Ask your Versely agent to set up reusable characters and products for a workflow
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.