Skip to main content
The OpenAIVideoSora2 node generates videos with OpenAI’s Sora models. It takes a text prompt along with an optional single reference image, sends the request to OpenAI, waits for generation to finish, and returns the resulting video. Supported durations and resolutions depend on the selected model. DEPRECATION NOTICE: OpenAI will stop serving the Sora v2 API in September 2026. This node will be removed from ComfyUI at that time.

Inputs

Constraints and Limitations:
  • The “sora-2” model only supports the “720x1280” and “1280x720” sizes; selecting “1024x1792” or “1792x1024” with “sora-2” raises an error. The larger sizes are available only with “sora-2-pro”.
  • When an image is connected, it must contain exactly one image; connecting more than one image raises an error.
  • Results are nondeterministic regardless of the seed value.
  • The displayed price estimate depends on the selected model, size, and duration.

Outputs

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): d19eb6b65d7f712278828e4b1f7105068cc5e7cb72813b7549ab24520e7719fc