Video generation models as world simulators
OpenAI introduces Sora, a large-scale text-conditional video diffusion model built on a transformer architecture that operates on spacetime patches of video and image latent codes. The model is trained jointly on videos and images of variable durations, resolutions, and aspect ratios. Sora can generate up to one minute of high-fidelity video and OpenAI frames scaling video generation as a path toward general-purpose physical world simulators.
Related guides (4)
Related events (8)
Sora Video Generation Model Launches at sora.com
OpenAI has publicly launched Sora, its video generation model, available at sora.com. The model supports video generation up to 1080p resolution and 20 seconds in length, with widescreen, vertical, and square aspect ratios. Users can generate content from text prompts or bring existing assets to extend, remix, and blend.
Sora System Card
OpenAI has published the system card for Sora, its video generation model capable of accepting text, image, and video inputs to produce video outputs. The model builds on techniques from DALL-E and GPT and is positioned as a creative storytelling tool. The system card documents safety evaluations, mitigations, and residual risks associated with the model's deployment.
Sora 2 System Card
OpenAI has released Sora 2, a new state-of-the-art video and audio generation model that builds on the original Sora. Key improvements include more accurate physics simulation, sharper realism, synchronized audio generation, enhanced steerability, and broader stylistic range. The accompanying system card documents safety evaluations and deployment considerations for the model.
Creating with Sora Safely
OpenAI published a safety overview for Sora 2 and the Sora app, describing the safety measures built into both the video generation model and its associated social creation platform. The post outlines concrete protections designed to address novel risks posed by state-of-the-art video generation. This represents OpenAI's public safety framing for the Sora 2 launch.
Sora 2 is here
OpenAI has released Sora 2, its latest video generation model, claiming improvements in physical accuracy, realism, and controllability over prior versions. The model introduces synchronized dialogue and sound effects as new capabilities. It is available through a new dedicated Sora app.
OpenAI Shuts Down Sora Video Generation Model, Redirects Team to World Models and Robotics
OpenAI is discontinuing its Sora video generation model, with web/app access ending April 26 and API access closing September 24, 2026. The model was losing roughly $1 million per day, with daily active users falling below 500,000 after peaking at 1 million post-mobile launch. The Sora team will be redirected to longer-term projects including world models and robotics, while compute resources have already been diverted to a new coding/enterprise model codenamed Spud. The shutdown also effectively ends OpenAI's high-profile partnership with Disney, which had planned to invest up to $1 billion contingent on Sora integration.
State of open video generation models in Diffusers
Hugging Face published a survey of open-source video generation models integrated into the Diffusers library as of January 2025. The post covers the current landscape of available open video generation models, their capabilities, and how they are supported within the Diffusers ecosystem. This serves as a reference for practitioners looking to use or compare open-weights video generation models.
Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation
This Hugging Face blog post details a workflow for fine-tuning NVIDIA's Cosmos Predict 2.5 world model using LoRA and DoRA parameter-efficient techniques for robot video generation tasks. The post covers practical implementation steps for adapting the foundation video model to robotics-specific domains. This represents a concrete application of world models to embodied AI, where synthetic video generation can support robot training data pipelines.