I built a visual reference finder with Jev One single prompt → 100 images from Cosmos, NASA, and The Met my new rabbit hole for creative work 🌻

really cool! lmk if you host that. also interested in how exactly you "prompted" jev. also how is it processing the images? through metadata? or does it actually receive the images as inputs?

metadata yes, for custom prompts I send structured choice questions: the brief + styles go in state, and my code supplies possible search phrases. Jev chooses one per source the app searches NASA and The Met’s APIs plus Cosmos’s public search page in parallel, then streams the images into the UI will share the link tomo

Did you just casually murder Pinterest? Can you put it online?

not trying to murder Pinterest 😅 you can run it here: repo: preview (no Jev): hosted preview is gallery + search only

jev supports image processing?

Looks cool! what does this do?

I send the brief + styles as stated, and my code gives it a list of search phrases Jev picks one phrase per source, then the app queries Cosmos, NASA, and The Met Jev reads titles and descriptions and can highlight one ref per source; my code fetches the images

Thanks for sharing, very creative!!

one prompt to 100 images is a good use for it.

100%, love it for my short form video brolls

Very cool.

thank u

Wow so beautiful!

🫶🫶

Integrating

that's really really cool!! Did you pre-fetch all data before?

Can you open the original museum page from an image on the board?

yes, try it here (same for @NASA resources):

interesting one

🙌

is it actually "looking" at the images to classify or just metadata?

metadata, it chooses search phrases, then reads titles + descriptions to highlight refs, my code pulls the pictures

ahh sweet

That sounds like an incredible way to use it for creative workflows. We actually went deeper on this here: