OpenAIVideoSora2 - ComfyUI Built-in Node Documentation

The OpenAIVideoSora2 node generates videos using OpenAI’s Sora models.

The OpenAIVideoSora2 node generates videos using OpenAI’s Sora models. It creates video content based on a text prompt and an optional input reference image, then delivers the generated video as its 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

Parameter	Description	Data Type	Required	Range
model	The OpenAI Sora model to use for video generation (default: “sora-2”)	COMBO	Yes	”sora-2" "sora-2-pro”
prompt	Guiding text; may be empty if an input image is present (default: empty)	STRING	Yes	-
size	The resolution for the generated video (default: “1280x720”)	COMBO	Yes	”720x1280" "1280x720" "1024x1792" "1792x1024”
duration	The duration of the generated video in seconds (default: 8)	COMBO	Yes	4 8 12
image	Optional input reference image used for video generation (fits, character, scene reference, etc.); only a single image is supported	IMAGE	No	-
seed	Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0)	INT	No	0 to 2147483647

Constraints and Limitations:

• The “sora-2” model only supports the “720x1280” and “1280x720” resolutions; the “1024x1792” and “1792x1024” options are valid only with the “sora-2-pro” model
• 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

Outputs

Output Name	Description	Data Type
output	The generated video file from OpenAI Sora	VIDEO

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