#Video

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.

AIKling 4.0 extends native single-pass video generation from 15 to 30 seconds and adds Multiple Keyframes supporting up to 10 keyframe images, versus Start & End Frames in Kling 3.0. It also expands reference inputs to up to 15 combined assets, including up to 5 videos totaling 30 seconds, and adds 10-bit HDR at 1080p and 4K. The all-new Kling 4.0 will officially launch in October, and Kling 4.0 Flash became available to a limited group of early-access users on September 28.

AIKling AI says Kling 4.0 will support native video generation from 3 to 30 seconds, with up to 10 keyframes for timing control. The full model is scheduled for October 2026, with early access to the new creation page rolling out from September 28.

AIKling 4.0 is entering early access, with a wider rollout planned for October, and Kling 4.0 Flash opens to Ultra Yearly subscribers on September 28. The update generates videos up to 30 seconds in a single pass, accepts up to 15 reference assets, and supports up to 10 keyframe images. Upcoming features include 10-bit HDR output at 4K and 1080p and video extension up to 2 minutes.

Why it matters: The post specifies concrete capability limits such as 30-second native generation, up to 15 references, and 10 keyframes, which help users judge fit for production workflows.

AIWatch the OpenAI 2026 Developer Conference in 100 seconds === Opus 5.5 is really fun. It's been out for a week, but I use it to make a few videos every day, and each video process lets me iterate and optimize my video workflow.

AIKrea announced Window Lab, an app built with Krea Agent, where users upload a video and adjust motion controls to get their desired result. The post invites readers to try the app through a linked demo.

AIGoogle Developers Blog describes how Sparse VideoGen (SVG) routes video diffusion attention heads into spatial or temporal sparse masks and implements them as custom JAX and Pallas Splash Attention kernels on TPU v6e. In isolated single-chip tests with 75.6K tokens and 10 heads, the sparse variants retain about 38.87% of query-key pairs. The article argues that theoretical sparsity must be converted into hardware tile skipping to yield real speedups.

AIDeedy describes a video generation pipeline built around Opus 5.5 in Claude Code, routing image, video, audio, and TTS models through OpenRouter's single API key. The workflow adds reference-image consistency, animatics before full renders, a critic skill that screenshots and transcribes output for QA, and ffmpeg for most editing.

AIA user ran qwen3-vl:32b-instruct locally through Ollama on a 128GB computer to auto-tag 40,000 images in their Eagle app. The image library was collected over 10 years and is intended as a personal asset base for Claude Code-made knowledge videos. The user says the use case makes the 128GB memory purchase feel worthwhile.

AIKrea, an AI creative platform, has published a dedicated video page at The post provides only this link, so no features, models, pricing, or capabilities are confirmed.

AIKrea has launched Draft Mode for Seedance 2.5, letting users experiment with 480p generations before switching to 1080p once a scene is right. The post directs readers to try the feature on Krea's platform.

AIReplicate has added P-Video-2-Pro, the latest video model from Pruna AI, which sits on the edge of the preference-speed and preference-price Pareto frontiers. Design Arena ranks its Quality and Speed variants tied for #2 on the Image to Video leaderboard with an Elo of 1325, with the Quality version generating in 8.0 seconds and the Speed version in 4.5 seconds.

AIKling AI says its Kling 4.0 Flash is live now for Ultra Yearly subscribers, with the full Kling 4.0 coming this October. The update advertises up to 4K resolution, 10-bit HDR output, stereo audio, and native 30-second generation. It also adds Omni Reference supporting up to 15 multimodal references and multi-keyframe control with up to 10 keyframes.

AIKling AI released THE BEAT, a short film created with Kling 4.0 that follows a drummer's journey back to the stage. The post promotes the piece with the tagline "WATCH ME PLAY" and provides no further technical details.

AIHiggsfield AI gave Claude Opus 5.5 access to 12 laptops, and from one prompt it split the work across machines using Computer Use and Higgsfield MCP. The system generated the visuals, built the animations, and assembled a fully editable After Effects project.

AIFelix Rieseberg asked Opus 5.5 to produce a timestamped supercut of their weekend work redesigning his personal homepage. The model generated the video, music included, from a single prompt.

AICreator CHunye produced the Japanese-style zombie short drama DUHAI entirely on his own from Episode 3 onward using SenseTime's Seko AI video creation agent. The series reportedly passed 74 million cumulative views on Douyin and beyond by Episode 9, with Seko handling workflows, characters, scenes, and props on one canvas.

AIBona Film Group announced that Sanxingdui: Future Past, a 100-minute film using AI throughout production, will screen nationwide on October 23, 2026. The production team says AI handled tasks like image generation while over 100 professionals kept creative control, and it took two years and over 1.2 million source images to maintain consistency across the film.

AIManus 2.0 introduces a new agent harness called Cascade, Manus Studio with Video Editor and Game Dev environments, and a standalone Cue app for personal agents. In one tested configuration, Cascade used 23.2% fewer tokens, completed tasks 28.2% faster, and cost 32% less to run than the previous system. Cue is in early access and available with an invite code.

Why it matters: The post separates the new agent harness, Studio, and Cue, and its Cascade chart gives measured token, time, and cost comparisons against the previous system.

AIHailuo AI promoted a weekend cartoon post, and a quoted clip by @awesome_visuals, titled "the chef's revenge," was made with MiniMax H3 Max. The post offers no further details on the model's features or performance.

AIGoogle's Jeff Dean says he is proud to have worked with many others on quite a few projects. The post is a brief reflection and names no specific products or figures.

AIDeedy shared a two-minute video about the history of Google that was generated by Claude. The post calls the result impressive but gives no details on the tools used or the video's production.

AIHiggsfield AI announced Seedance 2.5 at 1080p resolution on its API, offering 100% cashback for users. The post links to the Higgsfield API explore page for access details.

AIHiggsfield AI has introduced Seedance 2.5 in native 1080p on its API, positioned as a US-based option for commercial and large-scale productions. The company is offering 100% instant cashback on API spend from an $18M pool, with caps of up to $200,000 per business and $1,000 per individual, and unused cashback expires September 30.

AIKrea Agent now supports motion references, letting users take motion from any clip and apply it to a new character, scene, or element. The post invites readers to try the feature now.

AIHiggsfield AI released "Passport Rush," described as the first hybrid AI-animated short made with a Blender and Higgsfield pipeline. The film combines handcrafted 2D storyboards and 3D Blender previs with AI animation. The project is now open source, with every prompt and asset publicly available.

AIUsing the Neuron Kernel Interface, Reactor and Amazon's Neuron Science team built a kernel-centric path to real-time autoregressive diffusion video generation on Trainium. They addressed dynamic shapes, memory access patterns, and cache management, which are hard for generic compilers, and developed techniques intended to generalize across models.

AIAmazon Neuron Science and Reactor collaborated to optimize Rolling Forcing, an autoregressive diffusion video model, for real-time generation on AWS Trainium. The model generates 16 frames per second, the standard video playback rate, meeting latency requirements for streaming video generation.

AILuma says more post-shoot changes to wardrobe, background, and lighting can now be made without bringing the crew back to set. The post gives no details on the tools, pricing, or availability of this capability.

AIThis time I'm stunned: a product promo video made directly with Opus 5.5, with no AI video, AI music, or AI image generation models connected from start to finish, outputting both 16:9 and 9:16 versions in one go... The full prompt is posted directly below 👇 (1/3)

AIAlibaba Cloud's Wan3.0 workflow, run on Venice, produces a 10-second 1080p AI video for $1.82. The post argues that production cost, rather than output quality, will determine how much AI video content can scale.

AIRunway co-founder and Co-CEO Alex Germanidis explains why he sees world models as the endgame for AI video, with applications in robotics simulation and real-time generation. He also discusses how Sora pushed Runway into an intense competitive sprint and his vision of a fully neural operating system where interfaces are generated as pixels rather than HTML and code.

AIGoogle Research announced a new unified multi-agent framework that helps creators generate temporally consistent long-form video narratives. It is designed to reduce visual drift and the propagation of errors across the production pipeline.

AIGoogle DeepMind has launched Gemini 3.8 Live with Live Avatar, which adds near real-time visual presence to its native live dialogue models. The feature is available today in Gemini Enterprise, supports 97 languages with adaptive lip-sync, and allows custom avatars through enterprise allowlisting. All output carries an imperceptible SynthID watermark.

Why it matters: The post specifies the new avatar capabilities, the Gemini Enterprise access path, and the SynthID watermark, which helps readers judge its enterprise deployment fit.

AILiveKit has acquired Loophole Labs, an infrastructure company whose technology will enhance LiveKit's platform for building voice, video, and physical AI agents. The acquisition moves LiveKit closer to offering customers essentially unlimited concurrent agents, according to the company.

AIOdyssey launched Agora-2, a multi-agent world model that the company is making available for public experimentation. The post predicts such models will increasingly power applications in AI training, AI safety, robotics, autonomous vehicles, defense, energy, cybersecurity, and gaming.

AIOdyssey's research preview of Agora-2 lets up to 4 humans join forces against 16 agents in an environment simulated entirely in real time by a world model. The post states there is no game engine underneath.

AIGoogle introduced Gemini 3.8 Live with Live Avatar, which adds a visual persona with lip-syncing and expressions to its live dialogue models. The feature is available in Gemini Enterprise and supports 97 languages, with custom avatars available through enterprise allowlisting. Google says all output is watermarked with SynthID.

Why it matters: The post specifies enterprise availability, custom avatar allowlisting, and 97-language support, which clarifies who can use the feature and how far it reaches.

AIGoogle says Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enterprise, with US and EU endpoints, provisioned throughput, and enterprise compliance. Its video avatars use synchronized lip-syncing, custom avatars are limited to an allowlist, and generated audio and video carry SynthID watermarks. The model also understands and speaks 97 languages and can run tool calls in the background while the conversation continues.