#Video

AIFountain 0's new feature film ODYSSEUS: The Fall, directed by Ash Koosha, is now available in full with every shot generated by Kling 3.0. The team previously premiered Dreams of Violets at the 2026 Tribeca Festival as the first AI feature film accepted into a major film festival.

AIQwen's Wan 3.0 video model produced a complete fantasy fight between a mage and a swordswoman, with strong timing, poses, and complex layouts that the post calls anime-ready. The quoted post notes Wan is stronger than Seedance 2.5 on timing and layouts, while Seedance is better at keeping characters on-model, and that all three support Vid2Vid and Omni Reference.

AIMagical girl made with Wan3.0.

AI架空の商品に、どんな広告をつくる？ AZ8 × Wan「Ad from Zero」が開催中です。自由に考えた商品を、Wan3.0で一本のAI広告に。賞金総額3,000米ドル、制作クレジットも用意されています。 応募は9月24日まで。あなたのアイデアを、広告にしてください ↓ Translation: What kind of ad would you make for a fictional product? The AZ8 × Wan "Ad from Zero" contest is now open. Turn a freely imagined product into a single AI ad with Wan3.0. A total prize pool of US$3,000 and production credits are also available. Entries close September 24. Make an ad from your idea ↓

AIinclusionAI has published Realtime-Venus on Hugging Face with two 9B checkpoints: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for audio-only conversation. Both are built on MiniCPM-o 4.5 with a Qwen3-8B backbone and support full-duplex dialogue, proactive responses, and training-free long-video memory. The asynchronous Realtime-Venus-Harness runtime is hosted in a separate GitHub repository.

AIKling AI shared a photo trick for combining two images so they meet in the middle. The post gives no details on tools, steps, or results.

AIHiDream.ai launched vivago R1, a content creation agent, globally, with a domestic version upgrade. The company says R1 can output five-minute high-quality videos through agent planning, with a claimed 85% usable-output rate and support for multi-round extensions. It also released HiDream-O1-Video-1.0, a native omni-modal video model supporting single shots of 5 to 20 seconds at 1080p.

AIOdyssey announced Odyssey-3, a foundation world model it describes as a major step forward. The post claims it can control robots, power humanoids, drive cars, train AIs, pilot drones, and play video games, though it gives no benchmarks or technical specifications.

AIKling AI took part in TIFF: The Market 2026 on September 10 through an industry panel, networking reception, and on-site showcase. The company said the event explored how AI video is becoming part of professional filmmaking, from feature-length animation to real-world production workflows. Kling AI also said it continues to join leading film festivals such as Cannes and Toronto.

AIMiniMax Design lets a single brief drive a full production workflow on one canvas, with the Astra agent working in Blender through an official connector to build the scene and camera direction. The final video is generated with MiniMax H3 from the same canvas, with outputs syncing directly onto the canvas.

AIHailuo AI, owned by MiniMax, promotes its MiniMax H3 model as a way to create an army of characters without casting or catering costs. A creator, @koldo2k, says they used GPT-6 Astra-generated work to build a set and story, then animated it with MiniMax H3.

AIAt TIFF The Market, Kling AI hosted an expert panel and industry reception with filmmakers and tech leaders. The discussion explored how AI can make film production more affordable and accessible.

AIMiniMax H3 with SGLang-Diffusion and VDN-H3 generates 14.4 seconds of 768p video in 9.0 seconds end-to-end after warmup on 8× B200 GPUs. Eight-step denoising takes 6.9 seconds, exceeding 2× real-time, with no measured quality regression versus dense 50-step H3 across 103 test prompts.

AIThe Hailuo AI Bestiary contest closes tonight, September 14 at 23:59 PT, with $8,000 cash, 200,000 Credits, and ten Audience Choice awards. Entrants must submit a 30-second-or-longer short film generated with MiniMax H3 on any myth, era, or world.

AIMiniMax highlighted open-source community progress on its H3 video generation model, which it built with native stereo audio and multimodal reference control. Recent highlights include FastH3's 4-step distillation running on DGX Spark and Apple Silicon, and NVIDIA's Sol-H3 generating 15 seconds of 768p video with audio in 6.6 seconds on 8×B300 in a warm-inference benchmark. Other releases include VDN's faster-inference attention work with code and weights, and 8-step Acc-LoRAs from Alibaba PAI, with LightX2V offering 4- and 8-step Turbo LoRAs.

AIHailuo AI promotes bringing AI tools into professional 3D production workflows. A quoted post from @akiyoshisan describes connecting MiniMax Design, using GPT-6 Astra, to Blender via MCP for direct 3D creation. The creator says this lets 3D representation in Blender be built into an AI production flow rather than relying on MiniMax Design alone.

AIBill Peebles, OpenAI's former head of Sora, is teaming up with Hollywood mogul Jeffrey Katzenberg and investor Sujay Jaswa to create a new startup. The company will develop AI models for Hollywood, according to a report from The Information.

AIKling AI's official account invites followers to stop by its booth to see the product in action. The post offers no details about the event, location, or demonstrations.

AIFei-Fei Li announced on X that Atlas runs in real time. The post gives no further technical details, benchmarks, or availability information beyond the claim itself.

AIWorld Labs co-founders discuss Atlas, a world model for spatial intelligence, as the key to unifying pixel-level generation and reconstruction. The source says Atlas can digitally capture a 3D representation of a space from three photos, where previously 100 to 300 were needed.

AIAnthropic's Alex Albert says Fable 5.1 is strong at generating videos through code. Given a photo of a property lot, the model designed a house for it, rendered the design, and produced a cinematic walkthrough.

AIGoogle AI Studio says agentic video understanding is now available across Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite via the Gemini API. The company reports cost reductions of up to 66%, token consumption reductions of up to 88% and accuracy gains of up to 7% on standard video benchmarks. Developers enable it by setting processing to "agentic" in the API configuration, at standard token pricing.

Why it matters: The source gives concrete cost and token figures and explains how the agentic loop replaces fixed-rate frame ingestion, helping developers weigh it against their current video pipelines.

AIGoogle AI Studio has published a developer guide for agentic video understanding with Gemini. The post links to the guide on AI Studio's learning page but gives no further technical details.

AIGemini 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite now support agentic video understanding. The feature is available today for video uploads and YouTube videos through the Gemini API in Google AI Studio and Gemini Enterprise Agent Platform.

AIGoogle's Gemini 3.7 Flash accurately counts every clap in a video by using a new agentic video understanding capability that automatically adapts its processing speed. Static video processing defaults to 1 FPS, which can miss split-second movements or confuse claps with snaps and clicks.

AIin which the model decides what to watch, at what speed, and through which modality. It fetches only the moments and signals it needs instead of ingesting media at a fixed frame rate. The post says this cuts costs by up to 66% and token consumption by up to 88% while boosting accuracy, and it is available now via the Gemini API and in AI Studio.

AIAt an August 27 Ai2 event on expanding its work with the Paul G. Allen Research Center at Providence Swedish Cancer Institute, panelists identified five persistent challenges for scientific AI. The main ones are keeping AI steerable as research evolves, deciding which tasks to delegate, and avoiding the amplification of weak study design or bad data.

AIShanghai AI Lab's InternLM has published Intern Lumina U2, a 16B-parameter MoE model with 1B active parameters that handles text QA, image generation and editing, and image, video, and 3D understanding. The model uses an 8-codebook fully-discrete visual representation built on AToken. Checkpoints are provided for Huawei Ascend NPUs and NVIDIA GPUs under Apache 2.0, with the technical report still listed as coming soon.

Why it matters: The model unifies text, image, video, and 3D understanding with image generation in one framework, a broader scope than single-modality releases.

AIGoogle released agentic video understanding for Gemini 3.7 Flash, Gemini 3.6 Flash, and Gemini 3.5 Flash-Lite across the Interactions and GenerateContent APIs. The model dynamically navigates video timelines, requesting transcripts, frames, or audio tracks on demand. The source says this approach uses up to 88% fewer tokens for long-form content than static processing.

Why it matters: The changelog names the affected models and API surfaces, and states a token-use figure that helps developers judge the cost of long video workloads.

AIReplicate is offering Wan 3.0 at half price this weekend only. The post links to the Wan 3 model page on Replicate under Alibaba.

AIReplicate announced that Gemini Omni 1.1 Flash from Google DeepMind is now live on its platform. The update adds scene extension, control of a shot's starting and ending frames, video input references, upscaling to 4K, and 360p fast prototyping.

AIMiniMax-H3 on 8×H200 GPUs reaches 1.85–1.95x lossless speedup over Diffusers without approximation, with fixed prompts, seeds, resolution, FPS, and 50 denoising steps. Adding step reuse and sparse attention raises speedup to as much as 6.24x, but quality varies by workload, with SSIM from 0.76 to 0.91. Two presets trade off the two: a conservative Cache-DiT setting gives 2.99x at 0.90–0.98 SSIM, while a faster SubBlock 0.75 plus Cache-DiT stride gives 4.90–5.93x at 0.77–0.92.

AIGoogle is rolling out Gemini Omni 1.1 Flash updates in Google Flow, adding start and end frame controls to keep characters and narrative consistent between transitions. Creators can draft at 360p on lower credit cost, then export final clips in 720p, 1080p, or 4K for digital, social, or broadcast workflows.

AIReplicate has made Wan 3.0 Prime, the accelerated variant of Alibaba's Wan 3.0, available for text-to-video, image-to-video, and reference-driven workflows. The model generates clips up to 30 seconds long in a single shot with integrated audio-visual generation.

AIReplicate is offering a 30% discount on Alibaba's Wan 3.0 video model, available at The background post says Wan 3.0 generates native single-take videos up to 30 seconds long with synchronized audio.

AIReplicate has made Alibaba's Wan 3 available to try through a hosted demo page. The post links to the model page at and provides no further details on capabilities, specifications, or pricing.

AIGoogle shows Gemini 3.7 Flash, paired with Nano Banana and Omni, generating a fully animated parallax landing page from a single prompt. The model calls tools to write the copy, create image references, and render parallax-ready Omni videos.

AIByteDance has released Bernini-Diffusers-v2 on Hugging Face, a video generation and editing pipeline combining a Qwen2.5-VL planner with Wan2.2 diffusion components. The model card recommends it over Bernini-R for complex requests needing stronger instruction following and multi-step semantic planning. Code and weights are available under Apache License 2.0.

AIMeituan LongCat showed a demo in which a single prompt produced an immersive web landing page from a cinematic concept. The post is a short video teaser and gives no model name, version, or technical details.

AIMeituan LongCat turns one natural-language prompt into a full CG animation sequence, covering code, motion, and rendering. The post is a short demonstration video with no further technical details on the model or its performance.