Loading video...

Video Failed to Load

Go Home

an embedding space for Midjourney srefs. search for styles using natural language scrub through aesthetic properties like warm, cool, soft, sharp, muted, vibrant, emotions. then - copy the sref and use it in a prompt.

36,997 views • 1 year ago •via X (Twitter)

9 Comments

Silicon Jungle's profile picture
Silicon Jungle1 year ago

all of these images used the same prompt and seed - with a unique sref.

Silicon Jungle's profile picture
Silicon Jungle1 year ago

the best part? you can do embeddings math *on* midjourney styles. what’s the average of these two in the set? what do you get if you subtract heat and add cold?

Colonel Tasty🤌's profile picture
Colonel Tasty🤌1 year ago

You KNOW this is gonna be a banger tool when it's released. Great UX.

Silicon Jungle's profile picture
Silicon Jungle1 year ago

thank you!!

Dot&DM's profile picture
Dot&DM1 year ago

man, some people make the coolest things on the internet. it's like this mushroom hive mind!

richrd's profile picture
richrd1 year ago

oh yes, I neeeeed this. Thank you, pls release soon!

Silicon Jungle's profile picture
Silicon Jungle1 year ago

thank you!! 🙏

maxime bodereau's profile picture
maxime bodereau1 year ago

We have a crawling latent space on Do you want to try ? We have an api… I don’t understand how you use the Midjourney api, it doesn’t exist ?

Silicon Jungle's profile picture
Silicon Jungle1 year ago

i dont use the midjourney api

Related Videos

I just built an AI-powered creative search engine with Gemini Embedding 2 + Claude Code 🤯 Drop in your UGC clips, product shots, and ad variations — then search through everything in plain English. "Show me all the unboxing clips." "Find product shots with natural lighting." "Which creator talked about sensitive skin?" All inside Claude Code. Perfect for DTC brands and agencies sitting on hundreds of creative files they can never find when they actually need them. If you're digging through a folder of random file names, scrubbing through raw footage to find that one clip, and relying on memory to track down what's already been shot... This system eliminates the entire loop: → Drop your videos, images, and docs into a project folder → One prompt to Claude Code — it builds the entire search app for you → Google's new Gemini Embedding 2 model actually watches your videos and looks at your images → It understands what's inside each file — not just the file name → Search in plain English and get back the actual assets with confidence scores No scrolling through folders. No relying on file names to find anything. No re-shooting footage you already have. What you get: → A searchable library of every creative asset your brand has ever produced → Natural language search across video, images, and documents at the same time → Results that show the actual files inline — play videos, view images, read docs → A system that gets smarter every time you add richer descriptions to your assets One free API key. No monthly subscriptions. Runs on your machine. I put together a full playbook with the exact build prompt, the setup process, and DTC/agency use cases to get this running in under 30 minutes. Want the full playbook? > Like this post > Comment "SEARCH" And I'll send it over (must be following so I can DM)

Mike Futia

12,239 views • 3 months ago