pomelli
Create different variations of meta ads with just one URL.
What it does
Pomelli is a Brand-Consistent AI Ad Generator for Meta & TikTok. Input your product URL, and our AI analyzes selling points to auto-generate diverse ad creatives and variants. Rapidly A/B test to find winning ads and boost sales without manual design.
Turn simple product photos into high-converting Meta and X ads using our precise Image-to-Image AI. No product distortion, perfect for Shopify stores.
Stop wrestling with generic AI tools. Input your website URL, and Pomelli builds your Brand DNA to generate high-converting, platform-optimized static ad creatives for Meta, Instagram, and X. Explore high-fidelity ad variations generated by Pomelli. Every creative is meticulously crafted to maintain your unique brand identity while maximizing ROAS on Meta, Instagram, and X. Discover how performance teams use Pomelli to generate high-volume ads that feel 100% in-house and authentically aligned with their brand identity. Paste your URL and let Pomelli's AI map your core visual assets. Paste your product URL and Pomelli auto-scrapes product info, then uses AI to generate a default creative…from pomelli.pro
Does the same job
all alternatives →


Google Pomelli Catalog May 2026 · accounts.google.com · ▲142Turn a product catalog into branded campaign assets


More growth this month
the category →
AstraPixels▲267A pixel-art solar system at its real current positions.
Growth · 29d ago · astrapixels.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io


- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io


I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com