TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Laion-AI/erlich – Generate a logo from text with a latent diffusion model

3 pointsby bfirshalmost 3 years ago

1 comment

IceMetalPunkalmost 3 years ago
Every time I try out one of these (relatively) smaller diffusion-based text-to-image networks, it only makes me want DALL-E 2 access that much more. I tried "two corgis riding a dragon" and... well, I will have nightmares at what it generated.