Video AI
News on AI video generation, editing and animation
- Nvidia open-sources Flora to reduce robot video labeling costs Hardware & Robotics · Video
Nvidia has open-sourced Flora, a data engine that makes robot video labeling 125x cheaper than GPT-6 Astra. - When designing partition plates from caliper videos, Claude Opus 5.5 misread once like the real object, while GPT-6.1 Sol was correct all 3 times Models · Text · Video
When remaking pen holder partition plates with a 3D printer, a design test using caliper photos and videos was conducted. GPT-6.1 Sol… - Measured ComfyUI with 16GB VRAM: Images take 5–8 seconds per image, videos take about 2 seconds for 1–5 minutes (0.41.0) Workflows & Nodes · Image · Video
When running ComfyUI on my own PC, what I am most curious about is "how many seconds will this model take on my GPU?" Since internet… - datasocial/tiktok-5.6B-videos trends on Hugging Face Hugging Face · Video
The dataset datasocial/tiktok-5.6B-videos is trending on Hugging Face, with 29,890 downloads and 417 likes. - Moving "one illustration" with RX 9060 XT × Windows — Actual measurement records of pose correction, 10-second video, and AI inspection Workflows & Nodes · Image · Video
This is an actual measurement record of changing the pose of one anime-style illustration, turning it into an approximately 10-second AI… - AI model "Griffin" appears, which 48% of participants in video calls misidentified as human, reproducing face and body movements in video from a single image Models · Video · Image
AI company Tavus announced the AI model "Griffin," which interacts with humans using real-time video and audio. In an experiment using the… - Reka Releases Rho-1: A 19B Omni-Reasoning Model That Understands, Generates Video and Outputs Robot Actions in One Models · Text · Video
Reka has released Rho-1, a 19B omni-reasoning model that processes and generates text, images, video, and robot control actions in a…