Black Forest Labs 发布了 Flux 3，这是一款多模态基础模型，能够生成长达 20 秒的带原生音频的视频。这标志着一项重大进展，因为它是首个将原生声音生成直接集成到视频片段中的模型。初步评估表明，Flux 3 可能优于 Seedance 2.0 等竞争对手，该公司正在探索其在机器人和工厂自动化中的应用。 AI
影响 为 AI 模型中的集成视听生成设定了新标准，可能加速内容创作和机器人领域的应用。
排序理由 前沿实验室模型发布，附带系统卡。
AI 生成摘要 · Google Gemini · 来自 7 个来源。 我们如何撰写摘要 →
<p><img alt="" class="attachment-full size-full wp-post-image" height="1080" src="https://the-decoder.com/wp-content/uploads/2026/07/bfl_flux3_video.png" style="height: auto; margin-bottom: 10px;" width="1920" /></p> <p> Black Forest Labs has released Flux 3, a multimodal foundat…
FLUX 3 unifie image, vidéo et audio dans un seul modèle, et va jusqu'à prédire des actions pour la robotique. Une architecture qui change vraiment la donne, en Early Access. ⬇️ https:// bfl.ai/blog/flux-3 # MachineLearning # AI 📬 Ma veille dev de la semaine → https:// l.camillero…
🧠 # FLUX 3 segna un cambio di prospettiva per Black Forest Labs: non più modelli separati per immagini, video e audio, ma un’unica architettura multimodale progettata per apprendere una "rappresentazione coerente del mondo". 👉 I dettagli: https://www. linkedin.com/posts/alessiopo…
Black Forest Labs has released FLUX 3, a multimodal foundation model that generates images, video, audio and robot actions from a single architecture. The model produces up to 20-second video clips with native audio and outperforms competitors in human preference benchmarks. http…
Black Forest Labs launches FLUX 3 Video with native audio, multilingual dialogue, and agentic chaining for long-form sequences. Early claims suggest it outperforms Seedance 2.0, Grok Imagine, and others in multimodal tasks. # AI # Automation Source: Latent Space https://www. late…
Flux 3 generates videos with native audio up to 20 seconds long, a first for Black Forest Labs. Black Forest Labs unveils Flux 3, the first multimodal model generating videos with native audio up to 20 seconds, positioning itself ahead of competitors like Seedance 2.0 and explori…
Niemiecki startup Black Forest Labs wprowadza model Flux 3, rzucając rękawicę amerykańskim gigantom. System generuje 20-sekundowe klipy z natywnym dźwiękiem i już teraz pomaga w automatyzacji fabryk Audi. # si # ai # sztucznainteligencja # wiadomości # informacje # technologia ht…