PixVerse R2 - A real-time world model you can explore and change

PixVerse R2 is a real-time world model that generates continuously evolving audiovisual worlds instead of fixed video clips. It accepts text, images, audio and actions while generating, remembers what happened earlier in the session, and carries those changes forward in real time. R2 scales to longer, more coherent and controllable experiences — powering everything from interactive stories and characters to playable generative worlds.

Add a comment

Replies

Best
Maker
📌

Hey Product Hunt! 👋

We’re the PixVerse team. Meet PixVerse R2: a real-time world model you can explore and change while it’s being generated.

Explore. Change. Keep going.

  • Explore with WASD. Move through the world and choose where to go next.

  • Change it with a prompt. Introduce a new element or change the scene as it unfolds.

  • Keep going. Continue interacting in the same evolving world after each change.

A collection of R2-powered worlds is now open to explore.

How R2 works

R2 builds its world-model capabilities through continuous pretraining with Omni Causal AR, then distills that same foundation for real-time interaction. The aim is to make worlds more persistent, controllable, and scalable.

Whether you’re experimenting with interactive stories, game prototypes, or AI worlds, we’d love your feedback. What would you explore or change first?

The gallery combines AI concept scenes with an overview of R2’s architecture.

 Shoutout to this new launch, Jaden! Keep up the great work!

Thank you Justin🫶🏻

 Can R2 remember previous interactions across longer sessions ?

   Within an ongoing session, yes. R2 keeps recent interaction history alongside longer-term context, such as characters and the scene. It won’t remember every detail perfectly, though, and keeping things consistent over longer sessions is something we’re still improving.

Checked the gallery, and there are some really interesting worlds in there.
Definitely worth exploring.

Thanks and TEam....

Thanks so much, Deepak! Really glad you checked out the gallery 🙌 We’re excited to keep pushing R2 and see what kinds of worlds people build and explore with it. Appreciate the support!

 Thanks so much Deepak, love from PixVerse.

Which Vercel product did you use? What new capability did it give your team, and how did that shape the product you launched?
We built PixVerse R2's interactive web experience with Next.js on Vercel, which became important because R2 isn't a traditional generate-and-wait video product — it is a continuously running world that responds to users in real time. That infrastructure helped us turn R2 from a model demonstration into PixVerse World: a browser-based experience where anyone can step into AI-generated worlds, interact with characters, shape stories, and see the world respond as it unfolds.
congrats on the launch! pixverse has always been my go-to tool for aigc content production. Glad to see the new model and can’t wait to try it out!

 Thanks Alex!Congrats for your new career update!

This is just crazy where we're heading 😮 This looks really great! Congrats on the launch! The landing hero kinda made me feel a bit dizzy because some are really moving fast visuals so it was hard to focus on the text (but this just might be me). Otherwise you do a really good job at explaining the product upfront. The one other minor detail I noticed is the "muted" icon when I go to the gallery, that stripped musical note is not very common and I honestly though it looked a broken icon until I clicked it and saw the complete icon. Maybe use the same icons as you find in YouTube etc.? This is my 2c, wish you all the best with the launch!

Thanks Owen, for your support and suggestions😊

Hey everyone, Loqi from PixVerse here 👋

R2 lets you explore an AI-generated world with WASD and shape what happens next. We’re working on making those interactions feel natural and keeping the world consistent as you go.

Give it a try. If something feels off, tell us what you tried and what happened. That would help us a lot.

If you’d like to try more of PixVerse, feel free to DM me. Happy to share some extra trial credits.

Thanks for spending some time with it.

this is so fun! congrats on the launch! how do you ensure world consistency?

 Thanks, glad you had fun! R2 uses both recent interactions and longer-term context, like character identity and scene details, to guide what comes next. We also train it on examples where things drift, so it can learn to recover. It’s not perfect yet, and consistency over longer sessions is still a big focus for us.

 Thanks Helena, I know fish audio, a star startup that's doing exceptionally well in Silicon Vally, as a former Chinese female entrepreneur, I'm also proud of you all!

Really fun demo. I spent way longer than expected just testing random prompts 😅

 Glad to hear you already have fun with R2🫶

That's pretty damn cool! I was thinking on doing an emergence experiment with AI, perhaps this could be exactly the tool I need! Will certainly check this out

Thank u for loving it lol🫶🏻

 🫰🫰🫰

If you compare R2 to Decart Oasis and Google DeepMind’s Genie-style interactive world models, where do you feel you’re clearly ahead today (latency, controllability, multimodal input, session length, world consistency), and where do you think they have an edge?
12
Next