Updated
Updated
Items with an AI score under 20 are hidden. Show low-relevance items
Josh Woodward@joshwoodwardAI score22AIGoogle Flow now has more than 25 million people using it every month to create ideas, stories, and projects. Google is continuing to offer 50 additional daily credits to all users.
AIComfyUI's update makes the MiniMax H3 video VAE encode up to about 2.2x faster and decode 1.4-2.7x faster, cutting a 1344x768, 129-frame round trip on an RTX 5090 from 24.3 to 12.7 seconds. The gains come from a fused encoder kernel enabled by default, fp16 accumulation support in a custom convolution, and an int8 decoder, and the source says the changes are visually lossless to the eye. Users need ComfyUI v0.36.0 or above, and the int8 VAE file is a drop-in replacement for the standard one.
Alex Albert@alexalbert__AI score34AIAlex Albert, who is affiliated with Anthropic, says Opus 5.5 can use Blender to produce claymation-style animations from a single prompt on claude.ai. The post gives no further details on setup, limits, or availability.
OpenBMB@OpenBMBAI score23AIA developer connected a Raspberry Pi Zero W2 with a webcam and ambient microphone to MiniCPM-o 4.5, an open-source model running locally on a PC. The setup streams audio and video in real time with full-duplex interaction and no cloud APIs.
Xiaomi MiMo@XiaomiMiMoAI score36AIXiaomi's MiMo-V2.6 combines code, design, and tool use to build frontend interfaces, presentations, Figma-linked visual assets, and videos. The post says MiMo-V2.5-TTS supports narration in video production, and that the model can compose music, including an orchestral piece for around ten instruments that can be converted to MIDI. On Design Arena, the Pro version reportedly performs comparably to Claude Opus 5 and GPT-5.6 Sol.
Xiaomi MiMo@XiaomiMiMoAI score34AIXiaomi's MiMo team released MiMo Gallery, a showcase where every 3D model, game, slide deck, video, music piece, and image was generated by MiMo-V2.6. The post previews MiMo-V2.6 as an upcoming model and points readers to the gallery for a first look.
MiniMax Design (H3)@Hailuo_AIAI score22AIA community developer integrated the Jev method into MiniMax H3 to sparsify attention, deciding per layer which parts to keep. On an RTX 4070, video generation time dropped from 6 min 7 sec to 3 min 34 sec, a 41.7% reduction. The post notes that Jev selected sparsity rates of 1%, 3%, 5%, and 10% across 49 layers in 4-step generation.
Wan@Alibaba_WanAI score28AIA Wan 3.0 feature can change a video's camera angle while keeping the exact same action from the original clip, according to a shared example. The main post only thanks the author for sharing a prompt, so no further details are confirmed.
Wan@Alibaba_WanAI score22AIWan 3.0 lets users place their own photo into any scene and animate it using the Peel-Off Sticker skill on wan.video. The post presents this as a single-photo workflow but gives no further technical details.
Kling AI@Kling_aiAI score20AIVeteran film and TV producer Diane Shorthouse is exploring how AI can expand what filmmakers create, sharing her experience making MINIBOTS with Kling AI. The post says AI can support safer production and help bring emotional performances to AI characters.
MiniMax (official)@MiniMax_AIAI 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@theworldlabsAI 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@replicateAI 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.
Wan@Alibaba_WanAI 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_aiAI 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_WanAI 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.
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.
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@odysseymlAI 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.
MiniMax Design (H3)@Hailuo_AIAI 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 (official)@MiniMax_AIAI 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@radixarkAI 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 (official)@MiniMax_AIAI 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_AIAI 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_aiAI 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_palazzoloAI 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.
World Labs@theworldlabsAI 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@drfeifeiAI 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_NotebookAI 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_NotebookAI 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.
Google AI Studio@GoogleAIStudioPickAI 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@GoogleAIStudioAI 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@googleaidevsAI 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@googleaidevsAI 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@GoogleAIStudioAI 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.
World Labs@theworldlabsAI score34AIWorld Labs says its Atlas model understands both the spatial structure of the world and how it evolves over time. The company says this lets ordinary cameras be turned into a "bullet time" multiview capture studio that records dynamic moments frozen in time.
World Labs@theworldlabsAI score35AIWorld Labs says it pre-trained Atlas from scratch to accept multimodal inputs, including camera movement, and convert them into 3D-grounded views. The company says Atlas lets users direct views, reconstruct real spaces from their inputs, and build explorable worlds.
World Labs@theworldlabsAI score35AIWorld Labs says its Atlas model places multiple input views within a spatial context to generate image and video frames with precise control. The company demonstrates a hand-designed camera trajectory that produces a one-minute video at 1440p resolution from seven reference images.
World Labs@theworldlabsAI score46AIWorld Labs has introduced Atlas, which it describes as the first multimodal world model that generates image and video frames with pixel-perfect camera control. The model can also reconstruct the generated frames in 3D, letting users move the camera and simulate space and time.
