Updated
Updated
Showing low-relevance items too. Hide low-relevance items
Wan@Alibaba_WanOfficialAI score7AIWan, the account associated with Qwen, shares a link to video results on the OpenArt arena page. The post provides no model names, scores, or other specific figures.
Wan@Alibaba_WanOfficialAI score16AIWan3.0 placed second in the Overall Video category on OpenArt Arena, according to its developers. The post highlights support for 30-second takes, native audio, and any reference input for creators.
MiniMax (official)@MiniMax_AIOfficialAI score44AIVC-Attention, developed by Nunchux AI and collaborators, accelerates attention for MiniMax-H3 without retraining. In the B200 evaluation, it shows better fidelity than SageAttention2, with V-Smooth reducing value quantization error and ExpCast-FP8 speeding up softmax.
AIvLLM now supports NVIDIA hardware video decoding through PyNvVideoCodec, moving video decoding off the CPU so multi-GPU video captioning can scale to 8 GPUs. In benchmarks on 8xH100 GPUs, GPU-based decoding provides more than double the throughput of the CPU-based decoder for Qwen/Qwen3-VL-8B-Instruct with 8 single-GPU vLLM replicas. The functionality is included in standard CUDA vLLM releases, and PyNvVideoCodec==2.0.4 is required for custom installations.
World Labs@theworldlabsOfficialAI score32AIWorld Labs says its Atlas model turns 32 input images into a real-time flight through NVIDIA's Voyager headquarters. Trained on NVIDIA Blackwell GPUs, Atlas uses the images as 3D spatial context to generate new views with pixel-perfect camera control.
Replicate@replicateOfficialAI score33AIPruna AI has introduced P-Video-2-Pro, built on MiniMax H3, which generates 5-second videos at 480p or 720p in seconds. The model is 50% off for one week, starting at $0.01 per second.
Replicate@replicateOfficialAI score8AIReplicate invites users to try Pruna AI's p-video-2-pro model at the linked Replicate page. The post offers no further details on capabilities, pricing, or performance.
Wan@Alibaba_WanOfficialAI score44AIAlibaba's Wan3.0 video model now produces a single 30-second shot directly, up from 15 seconds and a year ago's 5-second clips. It adds director-level control and omni-reference input accepting up to five videos, letting creators generate long takes instead of stitching short clips. A filmmaker used Wan3.0 in a production workflow to make Soulscape and Johnny Mai.
Kling AI@Kling_aiOfficialAI score3AIKling AI's post links to a full film hosted at watch.fountain0.com. The post itself gives no further details about the film's content, production, or release.
Kling AI@Kling_aiOfficialAI score38AIFountain 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.
Wan@Alibaba_WanOfficialAI score34AIQwen'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.
Wan@Alibaba_WanOfficialAI score7AIWan (@Alibaba_Wan) shares a magical girl clip made with Wan 3.0. The post notes it is also a test of effect generation, so more magical girl content may follow. The clip was shared alongside the TapNow tool.
Wan@Alibaba_WanOfficialAI score15AIAlibaba's Wan and AZ8 have launched "Ad from Zero," a contest where participants create an AI ad for an imaginary product using Wan 3.0. The prize pool totals $3,000, with 3.5 million AZ8 credits offered for production support. Entries are open until September 24.
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.
Kling AI@Kling_aiOfficialAI score3AIKling 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.
Odyssey@odysseymlOfficialAI score38AIOdyssey 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.
Kling AI@Kling_aiOfficialAI score15AIKling 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.
MiniMax Design (H3)@Hailuo_AIOfficialAI score26AIMiniMax 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.
MiniMax Design (H3)@Hailuo_AIOfficialAI score16AIHailuo 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.
Kling AI@Kling_aiOfficialAI score12AIAt 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.
MiniMax (official)@MiniMax_AIOfficialAI score41AIMiniMax 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.
RadixArk@radixarkOfficialAI score43AIRadixArk's SGLang-Diffusion, paired with VDN-H3, generates 14.4 seconds of 768p video in 9.0 seconds on 8× B200 GPUs. The 8-step denoising alone takes 6.9 seconds, which is over 2× real time, and the team reports no measured quality regression against dense 50-step MiniMax H3 across 103 test prompts.
MiniMax Design (H3)@Hailuo_AIOfficialAI score9AIThe 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.
MiniMax (official)@MiniMax_AIOfficialAI score36AIMiniMax 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.
MiniMax Design (H3)@Hailuo_AIOfficialAI score22AIHailuo 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.
Black Forest Labs@bfl_aiOfficialAI score22AIBlack Forest Labs has released a FLUX video editing tool, with documentation and a public trial page linked in its post. The post provides no further details on capabilities, pricing, or limits.
Stephanie Palazzolo@steph_palazzoloXAI score36AIBill 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.
Kling AI@Kling_aiOfficialAI score4AIKling 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.
Fei-Fei Li@drfeifeiXAI score13AIFei-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.
World Labs@theworldlabsOfficialAI score37AIWorld Labs says its autoregressive model Atlas generates frames one at a time, and it has optimized a version that runs in real time. This lets users interactively explore worlds generated on the fly.
Fei-Fei Li@drfeifeiXAI score72AIWorld 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.
Gemini Notebook@Gemini_NotebookOfficialAI score28AIGoogle's Gemini Notebook has fully rolled out its international expansion of Short Video Overviews to all web users, adding support for more than 70 new languages and three new English variants. Mobile availability is coming soon, according to the post.
Gemini Notebook@Gemini_NotebookOfficialAI score28AIGemini Notebook now turns sources into roughly 60-second vertical videos called Short Video Overviews in more than 70 languages, plus three new English variants. The feature is rolling out on web and mobile for Ultra and Pro subscribers.
Alex Albert@alexalbert__XAI score18AIAnthropic'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.
Google AI Studio@GoogleAIStudioOfficialPickAI score75AIGoogle 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.
Google AI Studio@GoogleAIStudioOfficialAI score22AIGoogle 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.
Google AI Developers@googleaidevsOfficialAI score44AIGemini 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.
Google AI Developers@googleaidevsOfficialAI score34AIGoogle'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.
Google AI Studio@GoogleAIStudioOfficialAI score62AIin 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.
