#Video

AIHailuo AI says video editing with H3 is becoming seriously fun, pointing to a community test of MiniMax-H3-Character-Swap-LoRA in ComfyUI. The shared demo, posted by @toyxyz3, shows the LoRA being used for character swapping in video.

AIBen Affleck described fine-tuning open video models by freezing base weights and training only the last cinematic layer, using a learning rate of 2e-4. He said his company, InterPositive, built a private model per film from its own dailies after raising money to shoot a controlled dataset over eight months.

AIMatt Shumer reports that videos generated with Opus have appeared on LinkedIn. The post gives no further details on the videos, their creators, or how widely they are circulating.

AIYuchen Jin says no AI today can generate an Andrej Karpathy video from a prompt, and he hopes Karpathy will return, noting he has not uploaded a YouTube video in over a year. The post builds on Karpathy's suggestion that LLMs can produce bespoke explainer videos on arbitrary topics, though that idea is still emerging.

AINVIDIA has released PixelUMM, an encoder-free unified multimodal model with 15,199,672,064 parameters that handles text, image, and video understanding and generation directly in pixel space. It represents images as 16-by-16 RGB pixel patches on a Qwen3-8B language backbone, with iterative denoising for generation. The checkpoint is licensed for non-commercial research or evaluation only, while the source code is under Apache License 2.0.

AIThe author jokes about founding a consulting firm that would use agents for work, Griffin for meetings, and Griffin for interviews to fill remote roles. They then question whether remote engineers and consultancies would still be needed if that became reality. The quoted Tavus post says Griffin passed a video Turing test with 48% of live interlocutors believing it was human.

AIPika's app can convert any product image, including one taken on a phone, into a ready-made ad spot. A quoted post from @Gemalpha_88 shows a single product shot turned into a full cinematic ad using New Pika.

AIPika has released a set of new creation apps on its updated platform at pika.art. The post itself gives no further details about the apps' features or capabilities.

AIPika has released a Podcast Video app that lets creators easily stage two characters in a heated discussion. The post promotes the feature through a comic horror podcast clip made with New Pika, which is available at create.pika.art.

AIPika has launched Color Grade, a creative editing feature that applies a chosen tonality to any image or clip. It is normally used to adjust color footage but can also colorize black-and-white content.

AIPika has launched Camera Director, an app that reframes any shot to show it from different camera angles while preserving the original content. A quoted post praises its quality and says it is useful for real-world work.

AIPika has launched a new AI creative platform offering more than 40 apps covering needs from finishing edits to full video ads. The company describes the product as built for creatives and designed to meet exacting output standards.

AIArtist 852話 Hakoniwa made YUI, the first animated short film created with Comfy Agent, in three days of focused work for about 200,000 yen excluding labor. She used the Agent to regenerate shots, compare video models such as Wan, MiniMax H3 and Seedance, and check outputs against her character sheet. The main film was made mostly with Seedance 2.5, and the making-of video with MiniMax H3.

AIReplicate says it is powering Griffin from Tavus on its platform. Tavus describes Griffin as the first model to pass the video Turing test, with 48% of live conversation participants believing it was a real human. The model ranks first on NVIDIA's full-duplex AI video benchmark.

AIGamma Chief AI Officer Deeni Fatiha, Adobe Director Morgan Prygrocki, and Salesforce Global Brand Marketing's Shane Tapp discussed what changes when creative AI shifts from experimentation to production. The post gives no further details on specific tools, figures, or conclusions.

AIJulian Simcock of Harvard and Rick Ingram of Google DeepMind joined the Runway AI Summit to discuss regulating physical AI. The panel also covered policymaking and the race against China.

AIRunway Labs has introduced Project Continuum, a research application exploring operating-system-style interfaces built around real-time video. The announcement links to a short demo walkthrough showing the concept in action.

AINVIDIA announces that developers can build visual AI agents from a prompt using NVIDIA Cosmos and VSS 3.3. The post is a broadcast announcement that links to a live stream and provides no further technical details.

AIRunway introduced Visual Thinking, a new harness for coding agents that uses a real-time video model to visualize each step and tool call as it happens. The visualization lets users stay in the loop during complex autonomous workflows.

AIRunway says its system can expand any media into an interactive, real-time world simulation. The post presents this as turning fixed experiences into immersive multimodal simulations for both people and agents.

AIRunway describes Portals as visual elements with soft, dream-like edges that mark where generated content begins. Users can drag a Portal onto the page, where it sits alongside their content.

AIRunway says its real-time video model generates animated, interactive overlays called portals that illustrate any concept, place, or simulation while users browse. The post describes the feature as a demonstration without listing pricing, availability, or technical specifications.

AIRunway says its video model recomposes a scene with spatial awareness when the interface is resized. Users can click inside the output to interact with it directly in real time.

AIRunway Labs introduced Project Continuum, an operating system research application built around real-time video interfaces. The early look shows four interaction concepts: Portals, Visual Thinking, Responsive Video Interfaces, and Interactive Worlds. The post says Interface World Models such as Solaris are reimagining what an interface can be.

AICute in any time zone. 🐼 🎬 Dynamic Design, powered by SenseNova 6.8 Flash Preview, brings static images to life.

AIAlibaba's Wan 3.0 ranks #1 overall on the new Artificial Analysis AA-Video-T2V v2.0 text-to-video leaderboard, priced at $12 per minute of video. The benchmark judges models at 1080p using over 68,000 human preference votes across 1,000 prompts, and the author states Wan 3.0 leads 10 of 20 category boards.

AIOne of the most stylish H3 MVs yet. 👺🔥🧠

AIManus 2.0 introduces Video Editor, which lets users refine videos Manus generates, including changes to music, captions, and cut timing, without regenerating the entire video. The article describes Manus creating explainers, launch films, and animations from a single prompt, drawing on web search, video models such as Seedance 2.5, and code for motion graphics.

AIIn an in-depth Q&A, the Runway Research team discusses real-time models, generative interfaces, and future directions for robotics. The post gives no specific model names, benchmarks, or release details.

AIRunway's AI Summit is underway in San Francisco, with co-founder and co-CEO Anastasis Germanidis opening the day with a keynote. He argued that universal world simulators will be the most important technological development of our time. Further updates from the event are promised throughout the day.

AIHeyGen has released HeyGen Video, a production-quality video product built on MiniMax H3 and post-trained by HeyGen. Pricing starts at $0.01 per second through October, a 50% discount, aimed at businesses that need video without production-level costs.

AICreatify Labs released Boreal-H3, a video model built on MiniMax H3 and post-trained specifically for advertising. Reported results include 85.3% reference fidelity, brief success rising from 28% to 50%, and identity match improving from 83% to 94%. Visible defects per clip dropped 70%, while generation time and estimated cost fell 20%.

AIHiggsfield's full interface is now available inside Codex, powered by GPT-6.1 Sol, with access to local files and automation skills. The integration lets users automate creative workflows end-to-end within ChatGPT.

AINVIDIA says a single prompt can build and deploy a visual AI agent for a manufacturing line in under 30 minutes, with alerts, video search, and incident reports. The method uses the new Build Vision AI skill in NVIDIA VSS Blueprint 3.3, and a tutorial is available for readers who want to build one.

AIComfy API is now available to all users on a paid Comfy plan, letting them package a ComfyUI workflow with its custom nodes, LoRAs, models, and Python dependencies and deploy it as an autoscaling API endpoint. Builds capture the ComfyUI version and dependencies, and each immutable release gets its own URL, so the tested environment is the deployed one. Usage is billed separately, with GPU time charged by the second and storage prorated hourly.

Why it matters: The post explains how a ComfyUI workflow is packaged into immutable releases and deployed as an autoscaling endpoint, showing a path from local graph to production service.

AIMeetTwins, a beta app from Indian developer Aditya Shinde, is an AI assistant that attends Google Meet calls on its operator's behalf and relays only pre-approved information to colleagues. It uses AI models from Sarvam and can add a digital twin avatar created by Simli. If a participant types "/stop" in the chat, the bot leaves immediately, and anything outside the brief is referred to the operator by email.

AILuma introduces Ad Variants, a feature in Luma that produces multiple versions of a finished ad for different sizes and markets while keeping the same campaign. The post frames it as a way to extend an existing ad into localized formats without rebuilding each version.

AIKling AI showcased a short film generated by the full-powered KLING 4.0, which the source describes as the full-powered version. The background post from @hq4ai says the film was made with all-round reference generation, runs a native 30 seconds in 21:9 cinematic format, and offers clearer visuals and sound with more precise lip-sync than Flash. The same post states Kling 4.0 will launch in October.

AIInSpatio-World 1.5 from InSpatio_AI turns a single image, four images, a panorama, or a video into a navigable scene with wide viewpoint changes. The 1.3B model scores 68.72 on WorldScore-Dynamic, ranking first among evaluated real-time and interactive methods, with speeds up to 24 FPS. The post says the code is released under Apache 2.0 and that dependencies keep their own licenses.