Loverse Name-Prompt Studio

Per-product pipeline: for each product, Claude first reviews the actual artwork image and writes an art-director analysis of its essence (elements, palette, light, open space), then writes 2 variant(s) from what it sees (change the count in ⚙ Settings), and that product's renders start immediately while the next product is being written. 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. Want more style options? Raise the variant count in ⚙ Settings and press ⚡ again — products below the new count get topped up with extra variants from different scene elements, keeping everything you have.

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.

Models & rendering

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

AI model (analyzes the artwork & writes the name prompts — also powers the chat) Claude Opus 5 — best quality (default) Claude Opus 4.8 Claude Sonnet 5 — faster + cheaper Claude Haiku 4.5 — cheapest ChatGPT — GPT-5.1 ChatGPT — GPT-5 Qwen 3.8 Max custom model id…

The key for the chosen provider must exist as a Cloudflare secret (Settings → Variables and secrets, then redeploy): Claude → ANTHROPIC_API_KEY · ChatGPT → GPT_API (or OPENAI_API_KEY) · Qwen → QWEN_API (or DASHSCOPE_API_KEY). All models see the artwork image (vision) and follow the same rules and checks.

Image model on fal (renders the test images) Seedream 4.5 img2img edit (default — keeps your artwork, adds the name) Qwen Image Edit — img2img edit (keeps your artwork, adds the name) Seedream 4.5 txt2img — regenerates the whole scene from the prompt Qwen Image txt2img — regenerates the whole scene from the prompt Seedream 4.0 img2img edit custom fal model id… Test-render style Variants per product (how many different name-prompt ideas Claude writes for each product) 1 variant 2 variants — A/B (default) 3 variants 4 variants 5 variants 6 variants

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)

Status legend & how it works

🔴 MISSING PROMPTS	Not started — no name prompts written yet (fresh product, or you deleted its data). Press ⚡ WRITE + GENERATE.
🔴 ERROR · flagged	Claude's prompts failed the machine checks twice. Press 🎨 REGEN or ⚡ to retry with a fresh attempt.
🟡 NEEDS IMAGES	Prompts exist, some renders are missing or failed. ⚡ WRITE + GENERATE renders only what's missing.
🔵 RENDERING…	Working right now — the row updates live when each image lands.
🟠 TO REVIEW	Everything is rendered — compare the variants and ⬆ push the winner (or reject).
🟢 READY	You decided — a winner is pushed (or the product is rejected). It moves to the READY section and is included in the export.

Never-repeat memory: every variant you delete, reject, or replace with 🎨 REGEN is remembered per product and shown to Claude as a banned list — future writes must take a completely different creative direction. This memory survives deletes and even the full reset, so discarded styles never come back.
Placement rule: the name always renders ABOVE the child, in the top part of the artwork — enforced when prompts are written and again at render time.

⚠ Danger zone

Erases all prompts, renders, choices, pending jobs and history from the app so you can start completely fresh (for example after upgrading the prompt engine). Your products and these settings are kept. This cannot be undone.