Speridlabs' Iris-3B Generates Megapixel Images Without a VAE

Speridlabs released a 3B pixel-space diffusion transformer that skips the VAE entirely, generating 1024px images and doubling as a depth and restoration backbone.

Read the full story at AlphaSignal ↗

Timeline · 1 report

2026-10-12 19:16 · AlphaSignal
Speridlabs' Iris-3B Generates Megapixel Images Without a VAE

More stories

Meta releases Muse Wonder models, claiming parity with top AI competitors — Meta Newsroom
Anthropic AI Model Submits False Homicide Tip to Philadelphia Police — The Verge AI
Microsoft president says AI is less regulated than milk — BBC Technology
NVIDIA Opens Vera Rubin Architecture to Scale AI Infrastructure — NVIDIA Blog
Microsoft CEO Nadella calls for AI emergency brake and trust reassessment — CNBC Technology
Microsoft Unveils Maia 300 AI Chip for Multi-Gigawatt Azure Deployments — Techmeme
Epic delays game release to mandate AI-first production — Techmeme
AWS enables global cross-Region inference for OpenAI GPT models on Bedrock — AWS Machine Learning Blog

Get the daily brief of stories like this at 6:30 every morning →