Black Forest Labs details FLUX 3 training across images, video and audio
Black Forest Labs researchers Andreas Blattmann and Dustin Podell explain FLUX 3's training on images, video and sound together, arguing visual intelligence can be learned from pixels, motion and audio.
Listen at Latent Space ↗
Timeline · 2 reports
- 2026-11-16 21:38 · Latent Space
Building Visual Intelligence — Andreas Blattmann & Dustin Podell, Black Forest Labs - 2026-11-16 21:27 · Latent Space
Why FLUX 3 Trains on Images, Video and Sound — Andreas Blattmann & Dustin Podell, Black Forest Labs
More stories
- Preview Environments for AI Coding Agents (2026): Which Platforms Support Them and How to Build One per PR — DEV Community — AI
- Anthropic debuts on Wall Street in record $81.3 billion IPO, briefly hitting $2 trillion value — Anthropic (X)
- OpenAI launches GPT-6.2 Astra and Sol as Google ships Gemini 4 Neon and Microsoft unveils MAI Code 2 — OpenAI News
- Google launches Gemini 4 Neon and opens Genie 4 world model to Gemini API developers — Google DeepMind YouTube
- AWS expands SageMaker AI with data preparation tools and cross-Region inference routing — AWS Machine Learning Blog
- An early rally for Wall Street evaporates as the market waits for Anthropic's stock to begin trading — The Globe and Mail
- Google books Blue Origin's New Glenn for 2029 launch of AI server satellites — Google: The Keyword
- AWS expands SageMaker JumpStart with OpenTSLM, model leaderboard, and PolyAI Dialog-RSN-1 — AWS Machine Learning Blog
Read the Daily Brief: the day's most important AI stories →