Testing ChatGPT’s New AI Agent on my Stock Photo/Video Workflow – Part II

Following up on July’s Part I post, my ChatGPT credits have reset, so welcome to Part II, where I dive deeper into testing new strategies to optimise my microstock workflow.

Creating AI-Generated Images for Adobe Stock

This time I decided to tackle a hot (and slightly dystopian) topic: AI creating AI. Yes, I asked ChatGPT to not only research trending stock content but also to generate images with captions and metadata ready for Adobe Stock.

Here’s the exact prompt I gave it:

“I am stock contributor at Adobe Stock uploading AI-generated content to be licensed as stock. I want you to research top 3 AI-generated concepts to be created by you. Use strong sources such as best-selling content and whatever is trending these days, I will leave it to your discretion. Then I want you to provide me with captions and keywords for them, maximum 40 accurate keywords. You don’t need to upload to Adobe Stock as I will need to pass the CAPTCHA test myself, just give me these 3 assets as created with the metadata and I’ll do the rest. Work quickly!”

Fifteen minutes later, ChatGPT delivered five AI-generated “images” complete with metadata.

I recorded my entire workflow so you can watch the process (feel free to speed it up, I even encourage it).

Projected Earnings

Naturally, the next question was: how much money could these images actually make on Adobe Stock? Here’s the AI’s estimate for a two-year projection:

“Using these ranges for a rough two‑year (24‑month) projection for your five images:

  • Low‑end average ($0.02/image/month):
    Each image might earn about $0.48 over 24 months (0.02 × 24). Five images would total around $2.40.
  • Mid‑range ($0.10/image/month):
    At a mid‑level rate (10 ¢ per image per month), each image would earn about $2.40, so five images could generate roughly $12 over two years.
  • High‑end ($0.25/image/month):
    At 25 ¢ per image per month, each image might bring in $6.00 over two years, meaning all five could earn about $30.”

Honestly, I think these projections are pretty optimistic, but hey let’s check back in two years and see who’s right: me or the AI. Maybe it won’t even be accepted!

Manually uploading these files to Adobe Stock

Since the Agent gets stuck on the CAPTCHA to upload to Adobe Stock, I thought it would be much quicker if I just did it myself. I manually inserted all the metadata (captions, keywords, categories) and uploaded the files which was simple enough. Now, the waiting game begins.

What’s Next on the Segment?

I still have some credits left to burn, so here’s my question to you:

What else should I test?
Give me your best prompts, wild ideas, or workflows you’d like to see put to the test. I’ll happily run them through ChatGPT and share the results in the next installment.

Let’s push the limits of what AI can (and can’t) do for microstock contributors.

In any case, I’ll be back in a few days with my August Earnings and News Report. Hopefully I’ll have some book cover sales to report.


About Alex

I’m an eccentric guy. I am based in Lisbon, Portugal. I am on a quest to visit all corners of the world. I want to capture stock images & footage. I’ve devoted ten years to making it as a travel photographer / videographer and freelance writer. I hope to inspire others by showing an unique insight into a fascinating business model.

I’m proud to have written a book about my adventures which includes tips on making it as a stock travel photographer – Brutally Honest Guide to Microstock Photography

Leave a comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.