#视频

认识 Pika H3 Flex，今天首次亮相，成为 DesignArena 的 t2v 榜单上排名第一的开放权重模型。 它为专业迭代而打造，支持可导出的音频分轨、最高 4k 的分辨率，以及快于实时的生成速度。它能在短短 7 秒内生成一段带配乐的 15 秒片段。 所以，没错。这有点像是在炫技 💅

😳 This could be the scariest Halloween film you’ll watch today! Here’s the exact process we used to make it: But first: a big THANK YOU to @Kling_ai for sponsoring this video and making it possible! And if you want to learn more about my workflows, make sure to follow me! We at promptr teamed up with @NOMOREorg to create a film with AI that’s relevant to many people right now. We wanted to use our skills to create something with impact, something that normally isn’t visible but should be. We wanted to use AI the way we think AI should be used today. Everything in this film is AI-generated. After writing the script, we started by building the world: the monsters, the location, the general style. We iterated a lot with different models to create the start frames. That process took us two weeks. Then we generated the interviews with the monsters, and this is where some magic happened. Honestly, I was completely blown away by the realism that came out of Kling 4.0. The monsters look very lifelike, and the reason is that we didn’t force Kling to just repeat a written line. Instead, a prompt looked something like this: Prompt: Talking points – NOT a script! These are only the ideas Morris should get across. He answers completely in his own words, searches for them, improvises freely, and never reads them out word for word. I directed this whole piece more like I would direct real people on set, and I think that’s the way to go! Not micromanaging every little detail, but letting AI do its magic with guidance. Kling Flash was also VERY fast to iterate with, so we were able to create lots of takes and really choose the best ones. Share this film, send it to your friends, family and colleagues to make sure everyone in every country in the world knows nomoredirctory What do you think of the concept? What would you have done differently? I’d love to hear your thoughts. Made by PROMPTR AI Director: Simon Meyer AI Lead Artist: Lubbertus Mueller-Frick AI Artist: Ciro Kavouras Producer: Benjamin L. Schiller Sound Design & Mix: Krane & Rabe GmbH In collaboration with NO MORE Thomas Schmitt Arne Kreutzfeldt Dr. Georg Ramme Tim Sproten Ben Chimoy Elham Maddah Paul Alexander Probst Alysha Jeske Manuela C. Palencia Florian Boesel Kerstin von Kieseritzky

🚀 推出 Hy-Nomas：一个开源的自由形式交互式视频世界模型 主要特性： * 通过文本提示和相机轨迹进行自由形式交互 * 具备世界记忆的长时程生成 * 面向机器人等专业领域的轻量级 LoRA 适配 * 针对消费级 GPU 的推理优化 随时测试并反馈！ 🔗 网站： https://hy-nomas.hy.tencent.com/ 💻 GitHub：https://github.com/Tencent-Hunyuan/Hy-Nomas 🤗 Hugging Face： https://huggingface.co/tencent/Hy-Nomas 🎥 演示： https://hy-nomas.hy.tencent.com/demo #Hy#WorldModels #VideoGeneration #GenerativeAI

Today we're launching the Sunra API. Every leading image, video, audio and 3D model through one key, each at its maker's own API price. Pay as you go, with no subscription and no markup. The models are ready. Your app is next.

introducing Krea for Grok bot. generate images and video with the best models in the world, right from Grok. try it now 👇

卧槽，MiniMax H3 现在连消费级显卡都能跑了！ FastH3 Omni 正式开源！ 之前只能文生视频，现在直接升级全能模式： 图片、视频、音频都能作为参考 一次生成画面和同步音频 角色、动作、声音都能控制 支持消费级显卡本地部署 这波开源，AI 视频创作的门槛又要降了！🤣

More reference control. Fewer denoising steps. More places to run H3. The latest community contributions span 8-step reference-conditioned video + audio, 4-step distillation, sparse attention, and reference-token compression - alongside serving and workflow integrations across GPU servers, TPUs, and Apple Silicon. What matters is what this enables: more affordable experimentation, finer creative control, and more choices about where and how video generation runs. Open models become more useful when the community can improve the methods, adapt the runtime, and build workflows around them. Credit to @haoailab @yisun0618 @lanfeng491270 @guocheng_qian @Alissonerdx @ddalcu @tazmannner @HaochengXiUCB @huggingface @Jhuaplin, and the PTD, DMAD, SparkH3, TorchTPU and FlashML teams - including Zhengming Yu and zechengtang on GitHub. 11 additions to the H3 ecosystem index. Thank you to everyone building, testing, and sharing. https://github.com/MiniMax-AI/awesome-minimax-h3-integration

@Kling_ai 的 Kling 4.0 已于 D0 在 Runware 上线 🎬 支持最长 30 秒的 1080p 视频，带原生音频，此外还有： - 多关键帧支持，包括首帧、中间帧和尾帧 - 每次请求最多支持 15 个输入，涵盖关键帧、参考图像、参考视频和元素 - 基于提示词编辑现有片段 输出价格低至每秒 $0.133，未来 7 天在常规价格基础上享 15% 折扣。 它加入了我们 API 上已有的 19 个 Kling 模型，覆盖视频、图像、数字人和唇同步。 已经在 Runware 上调用 Kling 模型？将你的模型 ID 切换为 klingai:kling-video@4.0

Open weights. Shared progress. MiniMax H3 is moving fast. We built H3 for video generation with native stereo audio and multimodal reference control. The open-source community is making that capability faster, more accessible, and easier to build on. Recent highlights: • FastH3 — FastVideo, Nuva Lab and NVIDIA: 4-step distillation, now running on DGX Spark and Apple Silicon. • Sol-H3 — NVIDIA’s SANA team: 15 seconds of 768p video + audio in 6.6 seconds on 8×B300, in the team’s warm-inference benchmark.* • VDN — Haocheng Xi and the OpenVDN team: rethinking attention for faster H3 inference, with weights, training and inference code released. • PDD — NVIDIA’s distillation method, brought to H3 by Alibaba PAI as 8-step Acc-LoRAs, now supported in ComfyUI. • LightX2V — 4- and 8-step Turbo LoRAs, with workflows for text, image and reference-conditioned video + audio. Behind every release are people training, optimizing, quantizing, testing and sharing. Special thanks to: @haoailab @nuvalab @NVIDIAAI @xieenze_jr @HaochengXiUCB @ArashVahdat @julberner @LightX2V @ComfyUI And to the individual contributors pushing the work forward: @haozhangml @cxlcl1 @lawrence_cjs @yitongli165665 @haopengl33 @songhan_mit @shanasaimoe Thank you for building with H3 and helping make it faster, more accessible, and more useful for the community. Powerful models go further when we build together. Keep pushing H3. Excited to see what comes next. 🚀 Explore the ecosystem: https://github.com/MiniMax-AI/awesome-minimax-h3-integration

Build with Kling 4.0 on Runway Dev. Access it via API alongside the full Kling lineup and generate up to 30 seconds of native video with audio, with up to 15 references and 10 keyframes for precise control. Get 20% off Kling 4 through November 30. Start building at the link below.

🎬 Kling 4.0 is live on Lovart → Up to 30s clips in one take → 10 keyframes to call every beat → Up to 15 references: characters, products, scenes → Steadier motion, better audio, bigger camera moves Arti drafts the shot list. You direct the cut. @Kling_ai