{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-07-28T06:20:51.496Z","headline":"Black Forest Labs 发布 Flux 3：可生成带原生音频的 20 秒视频，并推出机器人动作模型 Flux-mimic","description":"德国 AI 公司 Black Forest Labs 发布多模态基础模型 Flux 3，可同时从图像、视频和音频中学习，首次支持生成带原生音频、最长 20 秒的视频。","url":"https://www.aioga.com/news/cmrxua5jb02kcroxpfp2mvtgm/","mainEntityOfPage":"https://www.aioga.com/news/cmrxua5jb02kcroxpfp2mvtgm/","datePublished":"2026-07-23T18:03:01.000Z","dateModified":"2026-07-23T18:03:01.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs","https://aihot.virxact.com/items/cmrxua5jb02kcroxpfp2mvtgm"],"canonicalUrl":"https://www.aioga.com/news/cmrxua5jb02kcroxpfp2mvtgm/","directAnswer":{"@type":"Answer","text":"德国 AI 公司 Black Forest Labs 发布多模态基础模型 Flux 3，称其可共同学习图像、视频和音频，并首次生成带原生音频、最长 20 秒的视频；公司还与 Mimic Robotics 开发了视频动作模型 Flux-mimic。","url":"https://www.aioga.com/news/cmrxua5jb02kcroxpfp2mvtgm/","dateCreated":"2026-07-23T18:03:01.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"the-decoder.com source article","url":"https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs","datePublished":"2026-07-23T18:03:01.000Z","provider":{"@type":"Organization","name":"the-decoder.com","url":"https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmrxua5jb02kcroxpfp2mvtgm","datePublished":"2026-07-23T18:03:01.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmrxua5jb02kcroxpfp2mvtgm"}}],"aggregationSource":"The Decoder：AI News（RSS）","originalPublisher":{"name":"the-decoder.com","url":"https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs"},"article":{"id":"cmrxua5jb02kcroxpfp2mvtgm","slug":"cmrxua5jb02kcroxpfp2mvtgm","url":"https://www.aioga.com/news/cmrxua5jb02kcroxpfp2mvtgm/","title":"Black Forest Labs 发布 Flux 3：可生成带原生音频的 20 秒视频，并推出机器人动作模型 Flux-mimic","title_en":"Flux 3 generates videos with native audio up to 20 seconds long， a first for Black Forest Labs","summary":"德国 AI 公司 Black Forest Labs 发布多模态基础模型 Flux 3，可同时从图像、视频和音频中学习，首次支持生成带原生音频、最长 20 秒的视频。","source":"The Decoder：AI News（RSS）","sourceUrl":"https://the-decoder.com/flux-3-generates-videos-with-native-audio-up-to-20-seconds-long-a-first-for-black-forest-labs","aiHotUrl":"https://aihot.virxact.com/items/cmrxua5jb02kcroxpfp2mvtgm","publishedAt":"2026-07-23T18:03:01.000Z","category":"模型更新","score":68,"selected":false,"articleBody":["German AI company Black Forest Labs (BFL) has released Flux 3, a multimodal foundation model that learns from images, video, and audio together. In BFL's early tests, it beat several rivals in video generation.","BFL describes Flux 3 as a step toward \"real-world visual intelligence,\" which it defines as models that can \"perceive, predict, and act across physical and digital environments.\" The company is part of a broader push to build so-called world models：https://the-decoder.com/google-deepmind-argues-video-generators-already-contain-the-world-models-computer-vision-has-been-missing/.","No single modality captures reality in full, BFL argues. Images show spatial structure, video captures how it changes over time, and audio can reveal links between mechanical events and the sounds they produce. Training on all three together lets them fill gaps for one another, giving the model more information than training on each modality separately. Ad","Flux 3 can now generate videos with native audio：https://bfl.ai/blog/flux-3 for the first time, with clips up to 20 seconds long. It supports text-to-video, image-to-video, video-to-video, keyframe-based transitions, multilingual dialogue, and agent-driven links between clips for longer multi-shot sequences. BFL says the model is especially good at human facial expressions and matching sounds to physical events. Ad DEC_D_Incontent-1","In early evaluations using 10-second clips at 720p, BFL reports that Flux 3 was preferred over Luma Ray 3.2 in 93 percent of comparisons, over Runway Gen-4.5 in 77 percent, and over Grok Imagine Video in 69 percent. The margins narrow against stronger competitors. Flux 3 was preferred over Kling v3 Pro 60 percent of the time, over Happy Horse v1 at 59 percent, over Happy Horse 1.1 at 57 percent, and over both Seedance 2.0 and Gemini Omni Flash at 52 percent each.","BFL says the results are preliminary, and no independent tests are available yet. Matching leading systems such as Seedance, which has already reached Hollywood：https://the-decoder.com/hollywood-wants-seedance-banned-and-reportedly-also-wants-to-keep-using-it/, and Gemini Omni Flash would put Flux 3 among the top video models. Ad","BFL also expects Flux 3 to improve image generation, especially for complex prompts and accurate text rendering in multiple languages. The company plans to release Flux 3 Image in early access within the next few weeks.","BFL says the model can also predict actions based on its understanding of the world. The company worked with Mimic Robotics to develop Flux-mimic, a video-action model：https://bfl.ai/blog/flux-3-mimic now being tested on production tasks at Audi. Ad DEC_D_Incontent-2","Flux 3 is based on Self-Flow：https://bfl.ai/research/self-flow, BFL's approach for teaching one model to generate and understand content at the same time. A multimodal transformer uses dedicated components to convert images, video, and audio into a shared internal representation and then turn it back into outputs. Ad","A component for actions provides the foundation for robotics applications. BFL says this unified learning process delivers better results than the previously standard flow-matching method, both in generation quality and in the model's grasp of the physical world.","BFL is rolling out all capabilities in stages, with early-access phases for feedback and safety testing. Flux 3 Video is：https://bfl.ai/models/flux-3 already available, and Flux 3 Image is set to follow in the coming weeks. Action prediction will initially be offered through select partners.","BFL also plans to release open-weight access to the multimodal backbone under the name \"Flux 3 Dev.\" Longer term, the company is working on next-generation models that aim to combine perception, action, and language prediction in a single model.","Stay in the loop on AI. Clear, useful, no fluff.","Follow The Decoder for AI news, background stories and expert analyses.","The Decoder：https://the-decoder.com/"],"articleImages":[{"sourceUrl":"https://the-decoder.com/wp-content/uploads/2026/07/bfl_flux3_video.png","alt":"Image description","afterParagraph":0,"url":"/media/articles/cmrxua5jb02kcroxpfp2mvtgm/741dfbfe14a3e0d2.png"},{"sourceUrl":"https://the-decoder.de/wp-content/uploads/2026/07/flux_3_video_bench-scaled.avif","alt":"","afterParagraph":5,"url":"/media/articles/cmrxua5jb02kcroxpfp2mvtgm/49b4490724abb4b8.avif"},{"sourceUrl":"https://the-decoder.de/wp-content/uploads/2026/07/flux_3_build-scaled.avif","alt":"","afterParagraph":8,"url":"/media/articles/cmrxua5jb02kcroxpfp2mvtgm/fb3e123b2cf9c219.avif"}],"mediaStatus":"ok","articleBodyZh":["德国人工智能公司黑森林实验室（Black Forest Labs, BFL）发布了Flux 3，一种多模态基础模型，可同时从图像、视频和音频中学习。在BFL的早期测试中，它在视频生成方面击败了多个竞争对手。","BFL将Flux 3描述为迈向“现实世界视觉智能”的一步，它将视觉智能定义为能够“在物理和数字环境中感知、预测和行动”的模型。该公司是构建所谓世界模型的更广泛推动的一部分：https://the-decoder.com/google-deepmind-argues-video-generators-already-contain-the-world-models-computer-vision-has-been-missing/。","BFL认为，没有单一模态能够完整捕捉现实。图像展示空间结构，视频捕捉其随时间的变化，音频可以揭示机械事件与其产生的声音之间的联系。对三者进行联合训练可以让它们互相填补空白，赋予模型比单独训练每种模态更多的信息。Ad","Flux 3现在可以首次生成带有原生音频的视频：https://bfl.ai/blog/flux-3，视频片段最长可达20秒。它支持文本到视频、图像到视频、视频到视频、基于关键帧的过渡、多语言对话，以及用于更长多镜头序列的由代理驱动的片段链接。BFL表示，该模型在处理人类面部表情和将声音与物理事件匹配方面特别出色。Ad DEC_D_Incontent-1","在使用720p、10秒视频片段的早期评估中，BFL报告称Flux 3在93%的比较中优于Luma Ray 3.2，在77%的比较中优于Runway Gen-4.5，在69%的比较中优于Grok Imagine Video。面对更强的竞争者时优势缩小。Flux 3在60%的时间内优于Kling v3 Pro，59%优于Happy Horse v1，57%优于Happy Horse 1.1，以及52%优于Seedance 2.0和Gemini Omni Flash。","BFL表示，这些结果为初步结果，目前尚无独立测试。若能匹配已经进入好莱坞的领先系统如Seedance：https://the-decoder.com/hollywood-wants-seedance-banned-and-reportedly-also-wants-to-keep-using-it/，以及Gemini Omni Flash，将使Flux 3跻身顶级视频模型行列。Ad","BFL还预计Flux 3将在图像生成方面有所提高，特别是在处理复杂提示和多语言文本准确呈现方面。公司计划在未来几周内推出Flux 3 Image的抢先体验版本。","BFL表示，该模型还可以基于对世界的理解预测动作。公司与Mimic Robotics合作开发了Flux-mimic，一种视频动作模型：https://bfl.ai/blog/flux-3-mimic，目前正在奥迪的生产任务中进行测试。广告 DEC_D_Incontent-2","Flux 3基于Self-Flow：https://bfl.ai/research/self-flow，这是BFL用于让一个模型同时生成和理解内容的方法。多模态变换器使用专门组件将图像、视频和音频转换为共享的内部表示，然后再转换回输出结果。广告","动作组件为机器人应用提供了基础。BFL表示，这种统一学习过程比之前标准的流匹配方法在生成质量和模型对物理世界的理解方面都能提供更好的结果。","BFL正在分阶段推出所有功能，并通过早期访问阶段进行反馈和安全测试。Flux 3 Video：https://bfl.ai/models/flux-3已可用，Flux 3 Image将在未来几周内推出。动作预测最初将通过精选合作伙伴提供。","BFL还计划以“Flux 3 Dev”的名义发布多模态骨干网络的开放权重访问。长期来看，公司正在研发下一代模型，旨在将感知、动作和语言预测结合于单一模型中。","保持对AI的关注。清晰、有用，无废话。","关注The Decoder以获取AI新闻、背景故事和专家分析。","The Decoder：https://the-decoder.com/"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"德国 AI 公司 Black Forest Labs 发布多模态基础模型 Flux 3，称其可共同学习图像、视频和音频，并首次生成带原生音频、最长 20 秒的视频；公司还与 Mimic Robotics 开发了视频动作模型 Flux-mimic。","background":"Flux 3 支持文本生成视频、图像生成视频、视频转视频、关键帧转场、多语言对话，以及由代理连接多个片段的多镜头序列。Black Forest Labs 称其早期测试中击败多家竞品，但结果仍属初步评估。","viewpoint":"Aioga 判断，Flux 3 的主要看点是把视频生成与原生音频、动作理解放在同一模型叙事中。不过，现有优势主要来自 Black Forest Labs 的早期测试，且材料明确表示尚无独立测试，结论仍需谨慎。","implications":"如果后续评测能够复现公司公布的偏好结果，原生音频与画面中物理事件的声音匹配可能提升视频生成的完整度。Flux-mimic 在 Audi 生产任务中的测试，也值得关注其从视觉内容生成走向动作预测的进展。","nextStep":"后续应重点核查独立评测是否出现，以及 Flux 3 在更强竞争对手上的表现是否稳定；同时关注 Black Forest Labs 计划在未来数周开放早期体验的 Flux 3 Image，以及 Flux-mimic 的生产任务测试进展。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-07-27T10:13:17.793Z","sourceHash":"97813ae253188be9","review":{"approved":true,"groundedness":95,"clarity":91,"duplicationRisk":12,"blockingIssues":[],"notes":["“Aioga 判断”属于明确标注的观点，不应视为来源事实；其内容总体基于材料并使用了谨慎表述。","“把视频生成与原生音频、动作理解放在同一模型叙事中”是概括性分析，可考虑改为更直接的事实表述，但不影响审核通过。","“原生音频与画面中物理事件的声音匹配可能提升视频生成的完整度”属于条件性推断，已使用“如果”和“可能”限定，未构成事实冒充。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","low-source-overlap","no-html","independent-ai-review"]}},"tags":["模型更新","The Decoder：AI News（RSS）"],"translations":{"zh-CN":{"title":"Black Forest Labs 发布 Flux 3：可生成带原生音频的 20 秒视频，并推出机器人动作模型 Flux-mimic","summary":"德国 AI 公司 Black Forest Labs 发布多模态基础模型 Flux 3，可同时从图像、视频和音频中学习，首次支持生成带原生音频、最长 20 秒的视频。","category":"模型更新","source":"the-decoder.com","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs 发布 Flux 3：可生成带原生音频的 20 秒视频，并推出机器人动作模型 Flux-mimic - Aioga AI资讯","description":"德国 AI 公司 Black Forest Labs 发布多模态基础模型 Flux 3，可同时从图像、视频和音频中学习，首次支持生成带原生音频、最长 20 秒的视频。","url":"https://www.aioga.com/news/cmrxua5jb02kcroxpfp2mvtgm/"},"en":{"title":"Black Forest Labs releases Flux 3: can generate 20-second videos with native audio, and launches robot motion model Flux-mimic","summary":"German AI company Black Forest Labs has released the multimodal foundation model Flux 3, which can learn from images, videos, and audio simultaneously, and for the first time supports generating videos up to 20 seconds long with native audio.","category":"Models","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs releases Flux 3: can generate 20-second videos with native audio, and launches robot motion model Flux-mimic - Aioga AI News","description":"German AI company Black Forest Labs has released the multimodal foundation model Flux 3, which can learn from images, videos, and audio simultaneously, and for the first time suppo...","url":"https://www.aioga.com/en/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:25:39.643Z"},"ja":{"title":"Black Forest Labs は Flux 3 を発表：ネイティブオーディオ付きの20秒動画を生成可能で、ロボット動作モデル Flux-mimic をリリース","summary":"ドイツのAI企業Black Forest Labsはマルチモーダル基盤モデルFlux 3を発表しました。これにより、画像、動画、音声から同時に学習でき、ネイティブ音声付きの動画を生成できるのは初めてで、最長20秒の動画に対応しています。","category":"モデル更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs は Flux 3 を発表：ネイティブオーディオ付きの20秒動画を生成可能で、ロボット動作モデル Flux-mimic をリリース - Aioga AIニュース","description":"ドイツのAI企業Black Forest Labsはマルチモーダル基盤モデルFlux 3を発表しました。これにより、画像、動画、音声から同時に学習でき、ネイティブ音声付きの動画を生成できるのは初めてで、最長20秒の動画に対応しています。","url":"https://www.aioga.com/ja/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:25:49.696Z"},"ko":{"title":"Black Forest Labs가 Flux 3를 발표했습니다: 원본 오디오가 포함된 20초 영상 생성이 가능하며, 로봇 동작 모델 Flux-mimic도 출시했습니다","summary":"독일 AI 기업 Black Forest Labs가 다중 모달 기초 모델 Flux 3를 출시했으며, 이미지, 비디오, 오디오에서 동시에 학습할 수 있고, 최초로 원본 오디오가 포함된 최대 20초 길이의 비디오 생성도 지원합니다.","category":"모델 업데이트","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs가 Flux 3를 발표했습니다: 원본 오디오가 포함된 20초 영상 생성이 가능하며, 로봇 동작 모델 Flux-mimic도 출시했습니다 - Aioga AI 뉴스","description":"독일 AI 기업 Black Forest Labs가 다중 모달 기초 모델 Flux 3를 출시했으며, 이미지, 비디오, 오디오에서 동시에 학습할 수 있고, 최초로 원본 오디오가 포함된 최대 20초 길이의 비디오 생성도 지원합니다.","url":"https://www.aioga.com/ko/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:26:30.352Z"},"es":{"title":"Black Forest Labs lanza Flux 3: puede generar videos de 20 segundos con audio nativo y presenta el modelo de movimientos robóticos Flux-mimic","summary":"La empresa alemana de IA Black Forest Labs lanzó el modelo base multimodal Flux 3, que puede aprender simultáneamente de imágenes, videos y audio, y es la primera vez que admite la generación de videos de hasta 20 segundos con audio nativo.","category":"Modelos","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs lanza Flux 3: puede generar videos de 20 segundos con audio nativo y presenta el modelo de movimientos robóticos Flux-mimic - Aioga Noticias de IA","description":"La empresa alemana de IA Black Forest Labs lanzó el modelo base multimodal Flux 3, que puede aprender simultáneamente de imágenes, videos y audio, y es la primera vez que admite la...","url":"https://www.aioga.com/es/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:26:28.895Z"},"fr":{"title":"Black Forest Labs publie Flux 3 : peut générer des vidéos de 20 secondes avec audio natif, et lance le modèle de mouvements de robot Flux-mimic","summary":"La société allemande d'IA Black Forest Labs a publié le modèle de base multimodal Flux 3, capable d'apprendre simultanément à partir d'images, de vidéos et d'audios, et prend pour la première fois en charge la génération de vidéos avec audio natif d'une durée maximale de 20 secondes.","category":"Modèles","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs publie Flux 3 : peut générer des vidéos de 20 secondes avec audio natif, et lance le modèle de mouvements de robot Flux-mimic - Aioga Actualités IA","description":"La société allemande d'IA Black Forest Labs a publié le modèle de base multimodal Flux 3, capable d'apprendre simultanément à partir d'images, de vidéos et d'audios, et prend pour...","url":"https://www.aioga.com/fr/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:27:05.226Z"},"de":{"title":"Black Forest Labs veröffentlicht Flux 3: Kann 20-Sekunden-Videos mit nativer Audioerzeugung erstellen und führt das Roboter-Aktionsmodell Flux-mimic ein","summary":"Das deutsche KI-Unternehmen Black Forest Labs hat das multimodale Basismodell Flux 3 veröffentlicht, das gleichzeitig aus Bildern, Videos und Audio lernen kann und erstmals die Generierung von Videos mit nativer Audioausgabe von bis zu 20 Sekunden Länge unterstützt.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs veröffentlicht Flux 3: Kann 20-Sekunden-Videos mit nativer Audioerzeugung erstellen und führt das Roboter-Aktionsmodell Flux-mimic ein - Aioga KI-News","description":"Das deutsche KI-Unternehmen Black Forest Labs hat das multimodale Basismodell Flux 3 veröffentlicht, das gleichzeitig aus Bildern, Videos und Audio lernen kann und erstmals die Gen...","url":"https://www.aioga.com/de/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:27:06.588Z"},"pt-BR":{"title":"Black Forest Labs lança Flux 3: pode gerar vídeos de 20 segundos com áudio nativo e introduz o modelo de ação robótica Flux-mimic","summary":"A empresa alemã de IA Black Forest Labs lançou o modelo base multimodal Flux 3, que pode aprender simultaneamente a partir de imagens, vídeos e áudios, sendo a primeira vez que suporta a geração de vídeos com áudio nativo de até 20 segundos.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs lança Flux 3: pode gerar vídeos de 20 segundos com áudio nativo e introduz o modelo de ação robótica Flux-mimic - Aioga Notícias de IA","description":"A empresa alemã de IA Black Forest Labs lançou o modelo base multimodal Flux 3, que pode aprender simultaneamente a partir de imagens, vídeos e áudios, sendo a primeira vez que sup...","url":"https://www.aioga.com/pt-BR/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:27:44.389Z"},"ru":{"title":"Black Forest Labs выпустила Flux 3: может создавать 20-секундные видео с оригинальным аудио и представила модель роботизированных движений Flux-mimic","summary":"Немецкая компания в области ИИ Black Forest Labs выпустила мультимодальную базовую модель Flux 3, которая может обучаться на изображениях, видео и аудио одновременно, впервые поддерживая генерацию видео с оригинальным звуком продолжительностью до 20 секунд.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs выпустила Flux 3: может создавать 20-секундные видео с оригинальным аудио и представила модель роботизированных движений Flux-mimic - Aioga Новости ИИ","description":"Немецкая компания в области ИИ Black Forest Labs выпустила мультимодальную базовую модель Flux 3, которая может обучаться на изображениях, видео и аудио одновременно, впервые подде...","url":"https://www.aioga.com/ru/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:27:44.471Z"},"ar":{"title":"Black Forest Labs أطلقت Flux 3: يمكنه إنشاء فيديوهات مدتها 20 ثانية مع صوت أصلي، وأطلقت نموذج حركة الروبوت Flux-mimic","summary":"أصدرت شركة الذكاء الاصطناعي الألمانية Black Forest Labs نموذجًا أساسيًا متعدد الأنماط يسمى Flux 3، يمكنه التعلم من الصور والفيديو والصوت في الوقت نفسه، ويدعم لأول مرة توليد فيديو بصوت أصلي يصل طوله إلى 20 ثانية.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs أطلقت Flux 3: يمكنه إنشاء فيديوهات مدتها 20 ثانية مع صوت أصلي، وأطلقت نموذج حركة الروبوت Flux-mimic - Aioga أخبار الذكاء الاصطناعي","description":"أصدرت شركة الذكاء الاصطناعي الألمانية Black Forest Labs نموذجًا أساسيًا متعدد الأنماط يسمى Flux 3، يمكنه التعلم من الصور والفيديو والصوت في الوقت نفسه، ويدعم لأول مرة توليد فيديو ب...","url":"https://www.aioga.com/ar/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:28:22.758Z"},"hi":{"title":"Black Forest Labs ने Flux 3 जारी किया: यह 20 सेकंड का वीडियो मूल ऑडियो के साथ उत्पन्न कर सकता है, और रोबोट मोशन मॉडल Flux-mimic भी लॉन्च किया","summary":"जर्मनी की एआई कंपनी ब्लैक फॉरेस्ट लैब्स ने मल्टीमोडल बेस मॉडल फ्लक्स 3 जारी किया, जो एक साथ इमेज, वीडियो और ऑडियो से सीख सकता है, और पहली बार नेटिव ऑडियो वाले, अधिकतम 20 सेकंड के वीडियो को जनरेट करने का समर्थन करता है।","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs ने Flux 3 जारी किया: यह 20 सेकंड का वीडियो मूल ऑडियो के साथ उत्पन्न कर सकता है, और रोबोट मोशन मॉडल Flux-mimic भी लॉन्च किया - Aioga AI समाचार","description":"जर्मनी की एआई कंपनी ब्लैक फॉरेस्ट लैब्स ने मल्टीमोडल बेस मॉडल फ्लक्स 3 जारी किया, जो एक साथ इमेज, वीडियो और ऑडियो से सीख सकता है, और पहली बार नेटिव ऑडियो वाले, अधिकतम 20 सेकंड के व...","url":"https://www.aioga.com/hi/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:28:22.526Z"},"it":{"title":"Black Forest Labs ha lanciato Flux 3: può generare video di 20 secondi con audio nativo e ha introdotto il modello di movimento robotico Flux-mimic","summary":"La società tedesca di intelligenza artificiale Black Forest Labs ha rilasciato il modello di base multimodale Flux 3, in grado di apprendere contemporaneamente da immagini, video e audio, e supporta per la prima volta la generazione di video con audio nativo della durata massima di 20 secondi.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs ha lanciato Flux 3: può generare video di 20 secondi con audio nativo e ha introdotto il modello di movimento robotico Flux-mimic - Aioga Notizie IA","description":"La società tedesca di intelligenza artificiale Black Forest Labs ha rilasciato il modello di base multimodale Flux 3, in grado di apprendere contemporaneamente da immagini, video e...","url":"https://www.aioga.com/it/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:28:57.778Z"},"nl":{"title":"Black Forest Labs lanceert Flux 3: kan 20 seconden video genereren met originele audio, en introduceert het robotactiemodel Flux-mimic","summary":"Het Duitse AI-bedrijf Black Forest Labs heeft het multimodale basismodel Flux 3 uitgebracht, dat tegelijkertijd kan leren van afbeeldingen, video's en audio, en voor het eerst het genereren van video met native audio tot maximaal 20 seconden ondersteunt.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs lanceert Flux 3: kan 20 seconden video genereren met originele audio, en introduceert het robotactiemodel Flux-mimic - Aioga AI-nieuws","description":"Het Duitse AI-bedrijf Black Forest Labs heeft het multimodale basismodel Flux 3 uitgebracht, dat tegelijkertijd kan leren van afbeeldingen, video's en audio, en voor het eerst het...","url":"https://www.aioga.com/nl/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:28:57.009Z"},"tr":{"title":"Black Forest Labs, Flux 3'ü yayımladı: 20 saniyelik, doğal sesli videolar oluşturabiliyor ve Flux-mimic adlı robot hareket modelini tanıttı","summary":"Alman yapay zeka şirketi Black Forest Labs, görüntü, video ve sesten aynı anda öğrenebilen çok modlu temel modeli Flux 3'ü piyasaya sürdü ve ilk kez yerel sesli, en fazla 20 saniyelik video üretimini destekliyor.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs, Flux 3'ü yayımladı: 20 saniyelik, doğal sesli videolar oluşturabiliyor ve Flux-mimic adlı robot hareket modelini tanıttı - Aioga AI Haberleri","description":"Alman yapay zeka şirketi Black Forest Labs, görüntü, video ve sesten aynı anda öğrenebilen çok modlu temel modeli Flux 3'ü piyasaya sürdü ve ilk kez yerel sesli, en fazla 20 saniye...","url":"https://www.aioga.com/tr/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:29:36.073Z"},"vi":{"title":"Black Forest Labs phát hành Flux 3: có thể tạo video 20 giây kèm âm thanh gốc, và ra mắt mô hình chuyển động robot Flux-mimic","summary":"Công ty AI của Đức Black Forest Labs đã phát hành mô hình cơ sở đa phương thức Flux 3, có thể học từ hình ảnh, video và âm thanh cùng lúc, lần đầu tiên hỗ trợ tạo ra video dài tối đa 20 giây kèm âm thanh gốc.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs phát hành Flux 3: có thể tạo video 20 giây kèm âm thanh gốc, và ra mắt mô hình chuyển động robot Flux-mimic - Tin tức AI Aioga","description":"Công ty AI của Đức Black Forest Labs đã phát hành mô hình cơ sở đa phương thức Flux 3, có thể học từ hình ảnh, video và âm thanh cùng lúc, lần đầu tiên hỗ trợ tạo ra video dài tối...","url":"https://www.aioga.com/vi/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:29:35.412Z"},"id":{"title":"Black Forest Labs merilis Flux 3: dapat menghasilkan video 20 detik dengan audio asli, dan meluncurkan model gerakan robot Flux-mimic","summary":"Perusahaan AI Jerman Black Forest Labs merilis model dasar multimodal Flux 3, yang dapat belajar sekaligus dari gambar, video, dan audio, mendukung untuk pertama kalinya pembuatan video dengan audio asli, hingga 20 detik.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs merilis Flux 3: dapat menghasilkan video 20 detik dengan audio asli, dan meluncurkan model gerakan robot Flux-mimic - Berita AI Aioga","description":"Perusahaan AI Jerman Black Forest Labs merilis model dasar multimodal Flux 3, yang dapat belajar sekaligus dari gambar, video, dan audio, mendukung untuk pertama kalinya pembuatan...","url":"https://www.aioga.com/id/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:30:11.577Z"},"th":{"title":"Black Forest Labs เปิดตัว Flux 3: สามารถสร้างวิดีโอ 20 วินาทีพร้อมเสียงดั้งเดิม และเปิดตัวโมเดลการเคลื่อนไหวของหุ่นยนต์ Flux-mimic","summary":"บริษัท AI ของเยอรมนี Black Forest Labs เปิดตัวโมเดลพื้นฐานมัลติโมดัล Flux 3 ซึ่งสามารถเรียนรู้จากภาพ วิดีโอ และเสียงพร้อมกัน และสนับสนุนการสร้างวิดีโอที่มีเสียงต้นฉบับยาวสูงสุด 20 วินาทีเป็นครั้งแรก","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs เปิดตัว Flux 3: สามารถสร้างวิดีโอ 20 วินาทีพร้อมเสียงดั้งเดิม และเปิดตัวโมเดลการเคลื่อนไหวของหุ่นยนต์ Flux-mimic - ข่าว AI Aioga","description":"บริษัท AI ของเยอรมนี Black Forest Labs เปิดตัวโมเดลพื้นฐานมัลติโมดัล Flux 3 ซึ่งสามารถเรียนรู้จากภาพ วิดีโอ และเสียงพร้อมกัน และสนับสนุนการสร้างวิดีโอที่มีเสียงต้นฉบับยาวสูงสุด 20...","url":"https://www.aioga.com/th/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:30:18.198Z"},"pl":{"title":"Black Forest Labs wydało Flux 3: może generować 20-sekundowe wideo z natywnym dźwiękiem i wprowadza model ruchu robota Flux-mimic","summary":"Niemiecka firma AI Black Forest Labs wypuściła wielomodalny model bazowy Flux 3, który może jednocześnie uczyć się z obrazów, wideo i dźwięku, po raz pierwszy obsługując generowanie wideo z natywnym dźwiękiem, o długości do 20 sekund.","category":"模型更新","source":"The Decoder：AI News（RSS）","aggregationSource":"The Decoder：AI News（RSS）","pageTitle":"Black Forest Labs wydało Flux 3: może generować 20-sekundowe wideo z natywnym dźwiękiem i wprowadza model ruchu robota Flux-mimic - Aioga Wiadomości AI","description":"Niemiecka firma AI Black Forest Labs wypuściła wielomodalny model bazowy Flux 3, który może jednocześnie uczyć się z obrazów, wideo i dźwięku, po raz pierwszy obsługując generowani...","url":"https://www.aioga.com/pl/news/cmrxua5jb02kcroxpfp2mvtgm/","contentTranslated":true,"sourceHash":"43960d4bd742285b","translatedAt":"2026-07-26T04:30:56.435Z"}}}}