Alibaba's Wan2.2 Animate Lets You Swap Characters Into Any Video
Alibaba's open-weights character animation model turns a single still image into a video that mimics any performer's motion and expressions, with ComfyUI running it on consumer GPUs.
// Intelligence
Video
A focused feed of models, agents, research and open-source releases for people building with AI.
Updated
Kyutai's CADRE Beats Rivals on Speed and Quality in Interactive World Models
Kyutai's CADRE replaces the laggy video autoencoders inherited from text-to-video models, letting interactive world models respond in real time on one GPU.
Abiray Shrinks Minimax-H3 Singularity V2 From 34 GB to 12.5 GB
A community pruning of the Minimax H3 Singularity V2 fine-tune shrinks the 34GB checkpoint to 12.5GB while keeping INT8 quality intact.
University of Göttingen's SiLVi Turns Animal Videos Into Relational Training Data
A new open-source annotator fills the gap between behavior labeling and bounding-box tracking, producing training data for interaction detection models.
Hao AI Lab's FastH3 Omni Generates Synced Video and Audio 9x Faster
An 8-step distilled MiniMax H3 that turns image, video, and voice references into clips with synced audio now runs natively in ComfyUI.
Black Forest Labs' FLUX 3 Max Generates 10-Second Videos 22x Faster
Black Forest Labs and fal shipped a post-trained FLUX 3 variant that renders a 10-second clip in 12 seconds, 22x faster than Seedance 2.5 at matched quality.
Google's Gemini Flash Cuts Video AI Costs 66% by Watching Smarter
Gemini now decides which video segments to actually look at, cutting long-form video analysis costs by up to 66% and token usage by up to 88%.
OpenFilm Lets Coding Agents Build and Edit Videos With Plain HTML
OpenFilm turns Claude Code, Codex, and other coding agents into video makers by representing films as HTML pages and a single frame(t) function.
huashu-motion Turns Any Coding Agent Into a Video Director for $0.27
A new open-source agent skill lets Claude Code and Codex build commercial-grade product launch videos directly in the browser, with point-to-edit control.
Jasna Slashes GPU Memory 77% While Running 5x Faster on Video Restoration
A trending open-source pipeline uses TensorRT and transformer-based detectors to reconstruct mosaic-censored regions in video at up to 5x the speed of prior tools.
GAASH Lab's QTrack Tracks Any Video Subject Using Plain English Descriptions
QTrack turns multi-object tracking into a language-conditioned reasoning task, hitting state-of-the-art on a new RMOT26 benchmark with just 3B parameters.
KiToke Keeps 89% Video AI Accuracy While Ditching 99% of Tokens
A training-free token compression method keeps Video LLMs accurate even when 99% of visual tokens are thrown away, with a 12.5x prefill speedup.
Pika Embeds Its Full Creative Studio Inside ChatGPT
Pika's image, video, and sound tools now live inside ChatGPT as a plugin extension with a sidebar panel, timeline editor, and shared library.
BeefTV Turns AI Video Production Into a Visual Node Graph
An open-source desktop canvas lets creators chain prompts, images, and video models into reusable AI storyboarding workflows, with assets stored locally.
Black Forest Labs Slashes FLUX 3 Video 4K Prices by 50%
Black Forest Labs slashed FLUX 3 Video's 2K and 4K pricing in half and doubled generation speed, challenging Kling at the premium tier.
Runway Brings Gen-4.5 and Aleph 2.0 to Private Enterprise Deployments
Runway is opening up its Gen-4.5 and Aleph 2.0 video models for private enterprise deployment on Baseten with fine-tuning and reserved GPUs.
Nanjing University's VideoJev Answers Video Questions 129x Faster Without Decoding
A new family of video models skips autoregressive text generation to score time spans and answer options directly, hitting over 100x QA speedups.
Motion2MixamoRig Turns a Phone Video Into a Rigged 3D Animation
A new open-source pipeline takes a single-person video and spits out a Mixamo-rigged GLB you can drop straight into Blender or Unity.
WanGP Runs Alibaba's Wan 2.1 Video AI on 6 GB GPUs
A community-maintained repackaging of Alibaba's Wan 2.1 video model lets 6GB consumer GPUs generate 480p clips through the WanGP toolbox.
UniForge3D Builds Complete 3D Models From a Few Unposed Photos
A new sparse-view 3D asset pipeline fuses reconstruction and generation in a shared coordinate space, with code and weights now public.
Google DeepMind's TapNet Unifies Seven Video Tracking Models in One Repo
Google DeepMind's TAPNet repository bundles every generation of their point tracker, from TAP-Net to TAPNext++, in one open-source hub.
Open-AI-Canvas Brings Self-Hosted AI Filmmaking to a Node Graph
A Chinese open-source infinite canvas workbench stitches scripts, characters, storyboards, and multimodal generation into a single node-based workflow for AI film production.
HiDream.ai's HiDream-O1-Video-1.0 Debuts at No. 6 Generating 1080p Videos With Synced Audio
HiDream's new omnimodal video model lands at #6 on the Artificial Analysis I2V with Audio leaderboard, generating 1080p clips with synchronized audio at $5.80 per minute.
Tencent's Youtu-Parsing-Omni Turns Seven Media Types Into One JSON Output
Tencent's 5B omni-modal parser handles documents, charts, geometry, audio and video into one structured JSON schema, rivaling Gemini-3-Pro.
No stories match these filters.