Skip to main content
The OpenAIVideoSora2 node generates videos using OpenAI’s Sora models. It creates video content based on text prompts and optional input images, then returns the generated video output. The node supports different video durations and resolutions depending 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

ParameterDescriptionData TypeRequiredRange
modelThe OpenAI Sora model to use for video generation (default: “sora-2”)COMBOYes”sora-2"
"sora-2-pro”
promptGuiding text; may be empty if an input image is present (default: empty)STRINGYes-
sizeThe resolution for the generated video (default: “1280x720”)COMBOYes”720x1280"
"1280x720"
"1024x1792"
"1792x1024”
durationThe duration of the generated video in seconds (default: 8)COMBOYes4
8
12
imageOptional input image for video generationIMAGENo-
seedSeed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0)INTNo0 to 2147483647
Constraints and Limitations:
  • The “sora-2” model only supports “720x1280” and “1280x720” resolutions
  • Only one input image is supported when using the image parameter
  • Results are nondeterministic regardless of the seed value

Outputs

Output NameDescriptionData Type
outputThe generated video outputVIDEO
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): b632ef33ca5f01a7aed780a9eeea9b2fcbf4ab85ccb8f026e6175ceaafbda47b