Google’s VEO 3 has been redefining what AI can do with video generation. Unveiled at Google’s I/O 2025 conference, this advanced model doesn’t just create realistic clips, it’s now capable of generating immersive 360-degree videos that can be experienced in virtual reality (VR).
Here's a collection of a bunch of the clips I created with VEO 3 to test out it's ability to generate 360° video.
I'll post a link below to a VR ready youtube video so you can test it on your own VR headsets. pic.twitter.com/yU966rNhGR
— Martin Nebelong (@MartinNebelong) June 6, 2025
Creating 360-degree videos with VEO 3 is surprisingly simple. By adding “make it 360 degrees” to a text prompt, users can generate spherical video content viewable in VR headsets or platforms like YouTube, which supports 360-degree playback. This capability, discovered by X user Henry Daubrez, wasn’t even a highlighted feature at launch, yet it’s already making waves. “We’ve been amazed by the excitement around Veo 3, which brings in a new era for video generation,” Google’s AI team shared in a post on X. “It’s state of the art in text-to-video, image-to-video, text-to-audio+video generation, and realistic physics.”
Sale
Meta Quest 3S 128GB — Dive into Mixed Reality — Unreal device. Unreal price. — All-In-One Headset...
- Explore thousands of immersive experiences with mixed reality, where you can blend digital objects into the room around you or dial up the immersion...
- Turn any room into your own personal theater. Dim the space around you and watch on a giant, vibrant screen. Go all in with USB-C headphones, or plug...
- Have more fun with friends in Quest. Whether you’re stepping into an immersive game with people from around the world, watching a live concert...
VEO 3’s ability to generate 360-degree content stems from its sophisticated architecture. Built on diffusion technology, the model learns by analyzing real videos, gradually adding noise until they’re static, then reversing the process to create new footage. Combined with a large language model for interpreting prompts and an audio generation system for sound, Veo 3 produces clips with startling realism. Josh Woodward, vice-president of Google Labs and Gemini, noted at I/O 2025, “The new model has even better visual quality, a stronger understanding of physics, and native audio generation.”
Available through Google’s AI Ultra subscription ($250/month) or the more affordable AI Pro plan ($20/month), the tool integrates with Flow, a web-based platform that combines VEO 3 with Google’s Imagen 4 and Gemini models. Users can describe scenes in plain language, describe characters, or adjust settings, making it approachable for those without technical expertise.
VEO 3 has already tackled prompts for open-world game scenarios, producing visuals reminiscent of Grand Theft Auto or The Last of Us. Extending this to 360-degree formats could revolutionize VR gaming, letting developers prototype immersive worlds quickly. “I kind of like the idea of being able to generate VR experiences that don’t exist yet,” Gizmodo’s Matt Kamen wrote, acknowledging the limited VR catalog.
Limitations exist, of course. VEO 3 outputs 360-degree videos at 720p resolution, and upscaling to higher resolutions remains unconfirmed. Glitches, like inconsistent physics or audio mismatches, can still occur.
[Source]
