Skip to content
IFAI

AI video

Industry tag872 stories

  1. IndustryReach 55

    YouTube forces creators to label realistic AI content

    YouTube just rolled out a new requirement forcing creators to label realistic AI-generated videos during the upload process. If your video depicts real people doing things they never did or fakes a real event, YouTube will slap an "altered content" tag on the description or directly on the video. Why it matters: With deepfakes surging ahead of elections, the platform is putting the burden on creators—and threatening to kill monetization for repeat violators.

  2. Generative mediaReach 33

    OpenAI confirms Sora will launch to the public this year

    OpenAI just confirmed that its buzzy text-to-video generator Sora will be publicly available later this year, potentially in "a few months." CTO Mira Murati revealed plans to eventually add audio and video editing features, while working to push operating costs down close to DALL-E levels.

  3. Generative mediaReach 39

    DeepMind alums launch Haiper with free AI video generation

    DeepMind alumni Yishu Miao and Ziyu Wang just launched Haiper, a fresh AI video platform backed by $13.8M in seed funding. Users can currently generate 2- to 4-second video clips or animate still images for free on its site. Haiper plans to build out a core model for developers and even explore open sourcing, taking directly on OpenAI's Sora.

  4. Generative mediaReach 32

    Lightricks unveils LTX Studio for longform AI video

    Lightricks just revealed LTX Studio, a platform that turns a single concept into a complete, multi-scene video with AI. It targets major pain points like maintaining consistent characters and lighting across cuts, aiming to make end-to-end AI filmmaking actually practical.

  6. Generative mediaReach 50

    Pika adds Lip Sync to give AI characters a real voice

    Pika just rolled out Lip Sync powered by ElevenLabs, allowing AI-generated characters' mouths to move in sync with spoken dialogue. Creators can type text prompts or upload their own audio tracks directly. For now, it is available in early access only to Pika Pro subscribers and invited Super Collaborators.

  7. Generative mediaReach 39

    Alibaba's EMO makes any photo sing and talk naturally

    Alibaba researchers just unveiled EMO, an expressive audio-driven portrait-video generation framework. Give it a single still image and an audio clip—talking or singing—and it animates the portrait with realistic facial expressions and head poses for any duration. It even keeps up with fast-paced rap and works across multiple languages, paintings, and 3D models.

  8. ResearchReach 37

    Google DeepMind’s Genie turns static images into playable games

    Google DeepMind just unveiled Genie, an 11-billion-parameter foundation world model that conjures playable 2D platformers from a single image or sketch. Trained on over 200,000 hours of unsupervised gameplay videos, it automatically infers character controls and physics. Why it matters: It turns static art into interactive worlds and could serve as an endless simulator to train future autonomous AI agents.

  9. IndustryReach 47

    Adobe creates 50-person CAVA research lab for video and audio AI

    Adobe just set up a new 50-person research group called CAVA, short for Co-Creation for Audio, Video, & Animation. Formed right after OpenAI dropped Sora, the team focuses squarely on generative AI for motion and sound. It signals Adobe is gearing up to defend its creative turf against frontier multimodal models.

  10. Generative mediaReach 35

    Will Smith parodies his viral AI spaghetti video

    Will Smith just dropped a hilarious Instagram clip parodying the infamous 2023 AI video of him devouring pasta. Coming right after OpenAI debuted Sora, Smith's real-life recreation highlights how quickly AI video generation evolved from a surreal nightmare meme to uncanny realism.

  11. Generative mediaReach 31

    OpenAI's Sora is officially heading to Copilot

    Microsoft just confirmed that OpenAI's Sora video generator will eventually make its way to Copilot. Advertising and web services CEO Mikhail Parakhin replied on X that integration is planned, though it will take time. There is no official timeline yet, but bringing text-to-video directly into Copilot promises to significantly expand its multimodal creative toolkit.

  12. IndustryReach 34

    OpenAI's Sora sparks a $10.21B AI crypto frenzy

    The AI crypto sector just added $10.21 billion in market value over 17 days, leaping 142.79% following OpenAI's reveal of text-to-video model Sora. Heavyweights like TAO jumped 145.38% alongside widespread triple-digit gains. Why it matters: Hype around generative AI can instantly reroute billions into speculative tokens, even before the model is publicly accessible.

  13. AI toolsReach 47

    OpusClip 3.0 turns long videos into shorts 300% faster

    OpusClip just rolled out version 3.0, introducing genre-specific curation models for formats like Q&As and webinars. It can generate clips up to 15 minutes long, runs 300% faster on hour-long footage, and adds AI b-roll and standalone captioning tools.

  14. AI toolsReach 44

    NBA's new NB-AI turns live games into Spider-Man cartoons

    NBA commissioner Adam Silver just revealed NB-AI, a voice-driven assistant built to personalize live basketball broadcasts. In a demo with rookie Victor Wembanyama, Silver commanded the tool to remake a live play "as if it were a Spider-Man movie," instantly transforming players into comic-style cartoon characters and letting viewers buy sneakers off players' feet in real time.

  15. ResearchReach 31

    Meta drops V-JEPA to teach AI how the physical world works

    Meta just unveiled V-JEPA, a non-generative video model designed to build human-like world models. Instead of predicting pixels, it predicts masked video parts in an abstract representation space, boosting training efficiency by up to 6x. Best of all, it excels at frozen evaluations—meaning you don't need to retrain the entire model for downstream tasks.

  16. AI toolsReach 32

    Disney tests AI tool to match ads with viewer emotions

    Disney is beta-testing a new AI tool called "Magic Words" that tags scenes across its catalog by content, brands, and emotional mood. Partnering with six global ad firms, the system lets brands run contextual ads on Disney+ and Hulu tailored to the exact vibe viewers are feeling, rather than relying on broad demographics.

  17. IndustryReach 34

    YouTube's 2024 vision puts AI front and center

    YouTube CEO Neal Mohan just outlined the platform's four big bets for 2024, placing generative AI right at the top. Mohan emphasized that AI should empower creators rather than replace them, spotlighting tools like Dream Screen for Shorts. Crucially, as deepfakes loom over global elections, YouTube will roll out transparent labels for realistic synthetic content in the coming months.

  18. Generative mediaReach 31

    Stability AI releases SVD 1.1 for more consistent AI video

    Stability AI just launched SVD 1.1, an upgraded image-to-video diffusion model tuned for better motion and visual consistency. Based on SVD-XT, it generates four-second, 25-frame clips at 1024x576 resolution from a single still frame. The weights are free for research on Hugging Face, while commercial use requires a paid membership or API access.

  19. Generative mediaReach 35

    How Guns N' Roses built an AI fever dream for 'The General'

    Creative Works London just revealed how they created the new music video for Guns N' Roses' track 'The General' using a hybrid generative workflow. The team built base scenes in Unreal Engine and fed them into Stable Diffusion to dream over each frame, creating uncanny, shifting imagery. It offers a practical blueprint for artists treating AI as a creative amplifier rather than a replacement.

  20. Generative mediaReach 53

    Runway lets creators animate multiple video elements at once

    Runway just rolled out Multi Motion Brush to all Gen-2 users, letting creators control independent movements across different parts of a static image. Users can brush several distinct zones and use sliders to tweak horizontal, vertical, and proximity motion for each layer. It gives video creators precise directional control rather than leaving the whole scene to AI guesswork.