PulseAugur
EN
LIVE 22:36:12

Black Forest Labs releases Flux 3 image and video model

Black Forest Labs (BFL), a company founded by former Stability AI researchers, has released its new image and video generation model, Flux 3. The model is trained on a combination of still images, video, and audio to develop a more comprehensive visual intelligence. This approach aims to improve temporal consistency and object understanding, as demonstrated by examples like a horse in motion and a person being panned around. BFL's work is inspired by the potential seen in models like Stable Diffusion, with a focus on efficient training and practical applications, including restoring old family photos. AI

IMPACT Sets a new direction for multimodal AI training by integrating audio and video, potentially improving object understanding and temporal consistency.

RANK_REASON New model release from a notable AI lab (BFL, spun out from Stability AI). [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on Latent Space (swyx) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Black Forest Labs releases Flux 3 image and video model

How we ranked this

Signal score
71 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
New model release from a notable AI lab (BFL, spun out from Stability AI). [lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Latent Space (swyx) TIER_1 English(EN) · swyx .ai ·

    Building Visual Intelligence — Andreas Blattmann & Dustin Podell, Black Forest Labs

    Black Forest Labs’ case for learning AGI from pixels, motion and sound.