Tag
This paper introduces SpheRoPE, a zero-shot and optimization-free framework that injects spherical priors into pre-trained diffusion transformers to generate 360 panoramic images and videos, overcoming topological constraints without retraining.
OpenAI researcher Kenji Hata and product lead Adele Li detail the major upgrades to ImageGen 2.0 on the podcast, including emergent capabilities such as text rendering, multilingual support, photorealistic quality, and 360-degree panoramas. Usage grew over 50% within two weeks of launch, with over 1.5 billion images generated weekly on ChatGPT.