[AINews] Black Forest Labs FLUX 3 - Multimodal Flow Models that beat Seedance 2.0, Gemini Omni and Grok Imagine, and FLUX-mimic video-action robotics model

Thursdays are the heaviest days for AI releases, and even though OpenAI scored a victory over Anthropic in launching the new ChatGPT Voice (consumer) and OpenAI Presence (enterprise) and getting more impressions than Claude Voice today (a completely accidental coincidence in timing, we are sure), neither seem as monumental as BFL’s launch of FLUX 3 Video today:

We last covered BFL in our very well received Anjney Midha podcast:

$5000 w…","cta":null,"showBylines":true,"showDescription":true,"showImage":true,"size":"sm","isEditorNode":true,"title":"The Professor of Outputmaxxing — Anjney Midha, AMP","publishedBylines":[],"post_date":"2026-06-18T17:30:00.811Z","cover_image":"https://substack-video.s3.amazonaws.com/video_upload/post/202359797/8dbbb3fa-e808-473c-af72-b9aee4fe0026/transcoded-1781652240.png","cover_image_alt":null,"canonical_url":"https://www.latent.space/p/anj","section_name":null,"video_upload_id":null,"id":202359797,"type":"podcast","reaction_count":22,"comment_count":4,"publication_id":1084089,"publication_name":"Latent.Space","publication_logo_url":"https://substackcdn.com/image/fetch/$s_!DbYa!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F73b0838a-bd14-46a1-801c-b6a2046e5c1e_1130x1130.png","belowTheFold":false,"youtube_url":null,"show_links":null,"feed_url":null}">

Most GenMedia people will remember the BFL homepage when they initially launched Flux 1 in 2024, hinting at video models next, with their logo in a forest. Well, 2 years later, it’s finally real:

The blogpost outlines Self Flow, covering ALL their modalities together with strong preference claims:

“ Its core capabilities include the following ( all outputs come with native audio generation ):

Text-to-video generation.

Image-to-video generation, either continuing from a starting frame (“animation”) or using images as visual references.

Video-to-video generation from a reference clip, carrying central elements of a sou…