Book the audit
All templates
Template · 2 to 3 daysE-commerce brandsCreator studiosAgencies

Studio Photo Generator

A Drive folder or Shopify admin upload triggers the run. Gemini 2.5 Vision describes each shot in structured form (subject, background type, lighting issues, crop problems). Gemini 2.5 Flash Image re-generates the product on a clean studio backdrop, prompt derived from the vision output. Real-ESRGAN upscales to 4096px. Output files named {sku}-{variant}-{hash}.webp write back to Shopify product media via the Admin API, or to Drive. 200 product shots in 40 minutes wall time at about $6 in model spend.

Book the audit · 30 minutes · No pitch

Tool-interchange map · every layer is swappable

Studio Photo GeneratorMODULE · 2 TO 3 WEEKS · RAW ASSETS TO STUDIO SHOTS01 · SOURCE02 · ANALYZE03 · GENERATE04 · DELIVER● DEFAULT● DEFAULT● DEFAULT● DEFAULTDrive folderDEFAULTGemini VisionDEFAULTGemini 2.5DEFAULTDriveDEFAULTOR SWAP IN vOR SWAP IN vOR SWAP IN vOR SWAP IN vDropboxS3AirtableNotionClaude VisionGPT-4VCloudinaryReplicateFFlux KontextDALL-EIdeogramReplicateDropboxAirtableNotionSlackANY OF THESE 5ANY OF THESE 5ANY OF THESE 5ANY OF THESE 5LLM LAYERGemini Vision · Claude Vision · GPT-4V · CloudinaryGEN LAYERGemini 2.5 edit · Flux Kontext · DALL-E · Ideogram · SDXLSTORAGE LAYERGoogle Drive · Dropbox · S3 · AirtableRaw product shots become studio-quality images before end of day.

What it does

Drop a folder of raw product shots. Gemini Vision analyses each image, describes the subject and any background issues, and routes it to an image generation model. Real-ESRGAN upscales the result. The finished file lands in Drive, Dropbox, or wherever the team picks up finished assets.

The generation step is intentionally swappable. Gemini 2.5's native edit mode is the default because it handles in-painting and background replacement without losing product detail. Flux Kontext and SDXL are valid alternatives for specific aesthetic requirements.

No photographer. No retoucher. No brief required for each image. The prompt template handles it from the analysis output.

Real-world use cases

Who actually uses this, and what changes for them.

Teams that recognise the pain

A Drive folder or Shopify admin upload triggers the run. Gemini 2.5 Vision describes each shot in structured form (subject, background type, lighting issues, crop problems). Gemini 2.5 Flash Image re-generates the product on a clean studio backdrop, prompt derived from the vision output. Real-ESRGAN upscales to 4096px. Output files named {sku}-{variant}-{hash}.webp write back to Shopify product media via the Admin API, or to Drive. 200 product shots in 40 minutes wall time at about $6 in model spend.

Before

Today, studio photo generator is a manual ritual. Someone owns the spreadsheet, the inbox, or the doc. The work is repetitive and rarely the highest-leverage thing they could be doing.

After

Studio Photo Generator runs as a wired pipeline. Triggers fire automatically, the model picks the right move, and the output lands in the tool the team already opens every day.

What changes for your team

  • The repetitive part of the job goes away. The judgement part stays.
  • Owner of the workflow gets a real job back instead of a copy-paste loop.
  • Outputs are consistent because the pipeline runs the same way every time, not the way someone happens to feel that morning.

Default tool stack

GGoogle Drive folderGGemini 2.5 VisionGGemini 2.5 Flash ImageRReal-ESRGANGGoogle Drive

Sample prompts

Time + scope

2 to 3 days

To ship

Fixed

Pricing model

Included

Source JSON

14 days

Tweak window

Live in these engines

Engine

buttermilk

Creator content production pipeline

→

Related templates

Template · 2 to 3 days

Appointment Router

Calendly fires the invitee.created event. Clay enriches the email (company, headcount, tech stack, LinkedIn). Claude Haiku picks the right rep from your round-robin config using tier rules (enterprise → enterprise AE, under 10 seats → PLG rep). HubSpot gets the contact plus deal in one upsert. The rep Slack DM lands with the prospect company, 3-bullet context, and the two most recent LinkedIn posts. All inside 18 seconds.

View →Template · 2 to 3 days

YouTube to 5 Platforms

Drop a YouTube URL into a Slack /repurpose command or a Notion row. n8n pulls auto-captions via the YouTube Data API (falls back to Whisper). Claude Sonnet runs 5 separate prompts with platform-specific word budgets: 550-word LinkedIn, 7-tweet X thread, 380-word newsletter section, 180-char Instagram caption with 5 researched hashtags, 75-second TikTok script. Typefully and Buffer each receive their queue via API. Review happens in one Notion page. Publish is one click.

View →Template · 2 to 3 days

Knowledge-Base Chatbot (RAG)

One workflow does the ingest: pulls Notion pages, Drive docs, PDFs, and 90 days of Slack channels on a nightly cron. Content chunked at 800 tokens with 100-token overlap; OpenAI text-embedding-3-large (3072 dims) writes into Qdrant with per-chunk metadata (source URL, last-updated, ACL tags). A second workflow is the chat loop: Slack @ask mention fires, top-8 chunks retrieved via vector search, re-ranked by Cohere Rerank, and Claude Sonnet answers with inline [1] [2] citations. P95 response: 3.2 seconds. New-joiner ramp time typically halves.

View →

Ready to ship this?

The audit takes 30 minutes.
The first template ships in days.

Book a call. I review your stack, confirm the fit, and we start the same week.

Book the audit · 30 minutes · No pitchSee all 12 templates →