The budget used to decide where a story got made. Jon Erwin made Moses on a stage in Manhattan Beach, with real actors and AI carrying them into any world the story needed.
Who's got the best open-source video world model when it comes to physics?💫 it's me again, MiniMax H3. Almost on par with closed-source sota.🍾
Check out Grok Imagine Video 1.5 Lite for yourself on the AA-Video Leaderboards: AA-Video-T2V v2.0: https://artificialanalysis.ai/video/leaderboard/text-to-video AA-Video-T2V-Silent v2.0: https://artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=false Or vote in the Video Arena: https://artificialanalysis.ai/video/arena
Artificial Analysis reports that Grok Imagine Video 1.5 Lite comes closest to the frontier in Architecture & Real Estate, Consumer, and Productivity & Knowledge Work use cases. It sits furthest from the frontier in Live-Action Film and Frontier use cases. Against Grok Imagine Video 1.5, Lite matches it in Social Media & Creator Content and trails it on the other nine use cases.
Artificial Analysis shares an AA-Video-T2V v2.0 text-to-video prompt, a 10-second product-page scene of a presenter revealing a volcano-shaped mist diffuser. The prompt specifies a shift from warm daylight to dim evening lamplight, fixed close-up camera angles, and consistent presenter and product appearance across shots.
Artificial Analysis reports that Grok Imagine Video 1.5 Lite comes closest to the frontier on AA-Video-T2V v2.0 in Multi-Scene & Narrative, Lighting & Materials, and Text Rendering. It is furthest behind in Dialogue & Lip Sync and Human Anatomy. Compared with Grok Imagine Video 1.5, Lite matches it in Physics and trails on the other nine capabilities, by the least in Multi-Scene & Narrative.
Grok Imagine Video 1.5 Lite sits on the quality and speed frontier on AA-Video-T2V-Silent v2.0 Among the 12 models on AA-Video-T2V-Silent v2.0 that we benchmark for generation speed, no model is both faster and higher quality than Grok Imagine Video 1.5 Lite. It generates a 10 second 1080p clip in a median of 60.5 seconds. Kling 3.0 1080p (Pro) scores slightly higher and takes 94 seconds for a 5 second clip. Vidu Q3 Turbo is 9 seconds faster on a 5 second 720p clip, and scores well below it.
Grok Imagine Video 1.5 Lite ranks ahead of Google's Veo 3.1 on AA-Video-T2V v2.0, at about a third of the price At 1080p with audio, Grok Imagine Video 1.5 Lite costs $0.14 per second, against $0.40 per second for Veo 3.1. It ranks #17 on AA-Video-T2V v2.0, two places above Veo 3.1. Against Grok Imagine Video 1.5, Lite costs 44% less at 1080p and ranks six places lower.
SpaceXAI's Grok Imagine Video 1.5 Lite ranks #17 on both AA-Video-T2V v2.0 leaderboards, ahead of Google's Veo 3.1 at about a third of its price. It is the fastest model at its quality level in Artificial Analysis benchmarks, with a median of 60.5 seconds for a 10-second 1080p clip, and it costs $0.14 per second at 1080p, 56% of Grok Imagine Video 1.5's $0.25 per second.
What a time to be alive. Claude Motion is so sick!
@nateparrott and team really cooked here. My entire timeline is filled with people making cool little videos with Opus 5.5, this makes it _way_ easier to do.
Learn more: https://runway.com/news/company-news/runway-claude-motion
Grok Imagine 🤝 OpenRouter https://openrouter.ai/x-ai/grok-imagine-video-1.5-lite
Stability AI's Interactive Research team introduced SemanTok, which makes early video tokens more semantically meaningful so the representation is easier to predict. According to the post, a model using SemanTok matches or beats the performance of a model more than three times its size. The approach targets more efficient autoregressive video generation.
Anthropic launched two beta features for Claude: Dashboards, which turns connected data sources like BigQuery, Databricks, Snowflake, or Salesforce into auto-updating live dashboards from text prompts, and Motion, which creates animated explainer videos from text, diagrams, and images. Dashboards is available to paid users and Motion to Team and Enterprise plans, while Docs, Slides, and Design leave beta and work across all plans, including free accounts.
Read more about the partnership - https://lumalabs.ai/news/Luma-Claude-Motion-Launch-Partnership
Bring your @claudeai Motion animation into Luma and keep going. Resize it for the formats you need, refine it, and make the versions ready to ship. Start in Claude Motion. Finish it in Luma. Claude Motion is in beta on Claude Team and Enterprise plans.
A ComfyUI developer generated 15-second 448×256 video in 15 seconds or less on one RTX 5090 using MiniMax H3 with FastVideo's FastH3 V2 checkpoint in four sampling steps. The setup combined sparse attention, a smaller ClipProj text encoder, a pruned INT8 checkpoint, and a fused FP4 MLP, cutting VRAM needs from 80GB to under 30GB. The custom ComfyUI node is open source.
Claude Dashboards and Claude Motion are in beta today. Ask Claude to turn your data into live dashboards and your ideas into animated explainers.
Don't sleep on domain-specific harnesses. Coding agents are great because of their harnesses, but they aren't built for creative work. Creative work needs its own harness. Voyager looks great. It's an open harness for video, graphics, and games. The agent works with your files and drives apps like Blender, DaVinci Resolve, and Unity right on your desktop. Bring Opus, Astra, or DeepSeek. Excited to try this one.
Voyager has launched a desktop app that lets AI agents work inside creative tools like After Effects, DaVinci Resolve, Blender, and Unity on a Mac. It reads project files, operates creative apps, and outputs editable results. > Video edits, motion graphics, and color grading in the apps creators already use. > 3D scenes in Blender and game prototypes in Unity. > Built-in skills, custom skills, and a memory that learns how each user works.
Actor Ben Affleck drew attention this week for explaining machine learning concepts, including convolutional neural networks, tensors, and transformers, in several recent interviews. He said he fine-tuned open video models by unfreezing weights and training only the last cinematic layer, using a dataset he built over about eight months for his startup. Affleck said he worries about students and learned helplessness more than Skynet, and predicted AI will be additive to the movie business.
Odyssey has launched Odyssey-3, its most powerful foundation world model, with a public research preview. Odyssey-3 Pro scored 66.1 on Physics-IQ Verified video-to-video with best-of-8 sampling, the highest reported result. The model generates environments from prompts and predicts changes in real time as users move through scenes.
The #1 video-to-video model in the Physics-IQ Verified benchmark is finally live! (Their research preview is) Odyssey 3 Pro is a world model, and nobody beats it for physical accuracy. You can use this model to control a robot, drive a car, play a video game, or pilot a drone. • It takes visual observations from the world • Uses these observations to learn how things work • Then maps that knowledge to the system's physical controls
We believe world models will power increasingly capable physical AI, generate environments to train intelligences, and enable new kinds of human experiences, and we believe Odyssey-3 is a big leap towards this. Experience Odyssey-3 today! https://odyssey.systems/meet-odyssey-3
Odyssey-3 is also just plain fun, able to generate diverse interactive environments that are only limited by your imagination.
Odyssey-3 is a foundation world model, enabling many applications in physical AI, human experiences, and even how we train intelligences. We're particularly excited by agents learning from experience inside Odyssey-3, working to accomplish objectives.
Odyssey-3 Pro sets a new state of the art on Physics-IQ Verified’s video-to-video benchmark, achieving 66.1, the highest reported score. Physics-IQ tests physical behavior across fluid dynamics, optics, solid mechanics, magnetism, and thermodynamics.
Odyssey-3 can generate interactive environments from a prompt, all in real time. It's a new kind of world simulator, and learns representations of physics, dynamics, and cause-and-effect from a broad dataset of visual observations.
Physical consistency is the most important feature of a world model, and the hardest to get right. That's why you see videos with objects defying gravity and people posing in impossible ways. Here is a complete evaluation of existing world models. Seedance 2.5 is the best right now.
Will we see double the number of Instagram accounts? @RyanSerhant just dropped a second Instagram page - this one is 100% AI-generated content with a HeyGen avatar of himself in different outfits. Love the transparency of it (rather than hiding its AI), and I think it’s smart to create a completely separate channel. If you have someone in your life that doubts the quality of AI avatars today, show them this new Instagram page.
Register here https://luma.com/jxtsiig2
What can you see from PixVerse at NABShowNY ? → Ideas turned into finished video → Faster creative iteration → Variations built for different channels See it live Oct. 21-22 at the Javits Center. Find us at Booth 565 Join us for a happy hour after Day 1 on October 21
Grok bot works great with foldable phones. Chat on the left, publish directly on the right.
Shengshu Technology has opened a preview of its Vidu Q4 video generation model, which supports native 4K output and up to 15 reference images and three reference audio clips. Testers generated a one-minute video for about 5.4 yuan, roughly 0.09 yuan per second at 720P, which the article says is a starting price that varies by resolution and mode. The Vidu Q4 preview is available through the Vidu platform, with the MaaS API priced at about 0.6 yuan per second for 720P image-to-video.
Pollo AI is using OpenAI's GPT-5.6, GPT-6 Astra, and GPT-Image-2.5 to help creators turn ideas into detailed images and cinematic video ads. The source gives no details on pricing, availability, or performance.
The author suggests installing a coding agent such as Pi or DeepSeek Harness in a cloud computer and allocating unused Code plan quota to it. Grok Bot could then use those tokens to write code and render videos, so leftover quota is not wasted.
Opus 5.5 on #MiniMaxDesign | Code Your Next Video Turn text into video—from code to motion. ✨ JavaScript Animation ✨ Motion Graphics ✨ Explainer Videos & Visual Storytelling ✨ Web & Product Demos More than a language model—it can interpret visuals and keep refining your creations.🎨
Muse, Dots, or other agents with cloud computers can all be used.
Tian Keyu's unnamed startup has raised nearly $30M from investors including 5Y Capital and IDG at a $200M post-money valuation, Bloomberg reports. The NeurIPS 2024 award-winning researcher leads a 10-person team developing a 200,000-symbol visual vocabulary to help AI process video. Tian claims the approach could cut video-generation costs at least tenfold. A full model release is planned for 2027; the company has no product yet.