Behind the scenes sneak peek 👀 Manipulate any character or object in your video, while keeping the rest perfectly intact. Become a Pika Creative Partner to get exclusive early access.

When Break-A-Scene creature 🤝 Action Editing

Reality is optional. Creativity is mandatory. Check out our upcoming Pika feature 🪄

Reality is just a rough draft. Check out a sneak peek of our new feature Pika!

Ever dreamed up a different ending to Harry Potter? Now’s your chance to make it real — rewrite the magic your way! 🪄 Pika

🚀 Excited to share OmnimatteZero: Training-Free Real-Time Omnimatte with Video Diffusion Models! 📄 Paper: arxiv.org/abs/2503.18033 🌐 Project: dvirsamuel.github.io/omnimattezero.… 🧵👇

Your videos, with a shocking twist. Introducing Pika Twists: manipulate any character or object in your footage, while keeping the rest perfectly intact. Available now at Pika dot art or on the iOS app.

Heading to #ICLR2025 to present, you guessed it, GameNGen 🎮 If you're into video games, video models, world models, or just excited about generative models, come say hi! — with Dani Valevski Yaniv Leviathan Shlomi Fruchter Poster #83 - Friday, 25th (10:00-12:00)

Hard to believe that in just 9 months, we went from an idea to an #ICLR2025 ICLR 2026 workshop with well over 100 attendees! Incredible talks, inspiring conversations, and so many new community members. I can’t wait to see where weight space learning will be in 12 months 🚀🚀🚀

CVPR returns this June. Join us Thursday June 12th for our annual CVPR Friends Dinner. RSVP at the link below.

New job, new reading list 📚 Excited to share I'm joining Runway in its journey to reshape the future of storytelling

Excited to share that I'm joining Runway! 🤩 Can’t wait to help build the next generation of creative tools for visual storytelling! 🔨📚

Happy to share I'm joining Runway 🎉 working on generative video models and tools! 📹

Sometimes the best way to express an idea is by sketching it out. A system from MIT CSAIL & Stanford captures this iterative process by teaching LLMs to create sequential sketches. It could work w/users to visually communicate concepts: bit.ly/4kfXFhk

Check out Omer Regev's latest demo!

Andrej Karpathy Thanks for the inspiring talk (as always!). I'm the author of the Model Atlas. I'm delighted you liked our work, seeing the figure in your slides felt like an "achievement unlocked"🙌Would really appreciate a link to our work in your slides/tweet arxiv.org/abs/2503.10633

Exciting news from #ICML2025 & #ICCV2025 🥳 - 🥇 VideoJAM accepted as *oral* at #ICML2025 (top 1%) - Two talks at #ICCV2025 ☝️interpretability in the generative era ✌️video customization - Organizing two #ICCV2025 workshops ☝️structural priors for vision ✌️long video gen 🧵👇

Introducing Act-Two, our next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking. Act-Two only requires a driving performance video and reference character. Available now to all our Enterprise