Loverse Name-Prompt Studio

–

written

–

flagged

–

remaining

Writes 2 variant(s) per product (each from a different scene element — change the count in ⚙ Settings), one product at a time, following your rules and the 16-product library. Machine checks run on every result; safe to stop and resume any time — nothing already written is touched. Rewrites keep the old version in History. ⚡ Write + render everything runs the whole batch in one click: it writes every missing prompt, then renders every missing image.

–

images done

–

to render

One image per variant, rendered with img2img on the product's own store artwork (the portrait stays untouched — only the name is added) with the test name (Clara / Michael). 6 render in parallel; failures are logged and can be retried; safe to stop and resume. Re-renders keep the old image in History.

Nothing to review yet — write prompts and generate images first.

keys: 1…6 choose variant (← A · → B) · ↓ reject · space next · click image to zoom

Models & rendering

Changes save to the app and apply to the very next write / render — no redeploy needed.

Claude model (writes the name prompts) fal model (renders the test images) Test-render style

Add name to the product photo — keeps your artwork exactly as-is, only adds the lettering (recommended) Re-generate the full scene — sends the whole prompt, like the production pipeline does with customer photos

Variants per product (how many different name-prompt ideas Claude writes for each product)

Applies to prompts written from now on. Products that already have prompts keep their current variants until you press ↻ regenerate on them. More variants = more Claude + render cost per product.

Image size for renders (keep it matching your artwork's 3:4 shape; blank or "auto" = model default, which can cause frames)

Everything ever written, rendered or chosen — kept until you delete it here.

Models & rendering

Team password