Wan3ImageToVideoApi - ComfyUI Built-in Node Documentation - ComfyUI

This node generates a video from a first-frame image using the Wan 3.0 model. You can optionally provide a last-frame image to control how the video ends; the model then creates a video that transitions from the first frame to the last frame.

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
`model`	Selects the Wan 3.0 model variant to use and determines which model-specific settings are shown below.	DYNAMIC_COMBO	Yes	”wan3.0-video" "wan3.0-video-prime”
`first_frame`	First frame image. Exactly one image is required.	IMAGE	Yes	Single image
`last_frame`	Last frame image. The model generates a video transitioning from first to last frame. Optional; if provided, exactly one image is required.	IMAGE	No	Single image
`seed`	Seed to use for generation (default: 42).	INT	Yes	0 - 2147483647
`watermark`	Whether to add an AI-generated watermark to the result (default: false).	BOOLEAN	Yes	true false

wan3.0-video and wan3.0-video-prime Inputs

These model-specific settings are shared by both model options and appear when a model is selected.

Parameter	Description	Data Type	Required	Range
`prompt`	Prompt describing the elements and visual features. Supports English and Chinese. Can be left empty (default: empty).	STRING	Yes	Up to 20000 characters
`resolution`	Resolution of the output video.	COMBO	Yes	”1080P" "720P" "480P”
`ratio`	Aspect ratio of the output video. With “adaptive”, the output dimensions are derived from the first frame.	COMBO	Yes	”adaptive" "16:9" "9:16" "1:1" "4:3" "3:4”
`duration`	Output duration in seconds. With “auto”, the model chooses a duration that fits the prompt.	COMBO	Yes	”auto" "2” - “30”
`audio`	Whether the output video contains an audio track (default: true).	BOOLEAN	Yes	true false
`prompt_extend`	Whether to enhance the prompt with AI assistance (default: true).	BOOLEAN	Yes	true false

Note: The node accepts exactly one first_frame image and optionally one last_frame image. If more than one image is connected to either input, an error is raised. When last_frame is provided, the generated video transitions from the first frame to the last frame. The prompt is limited to 20,000 characters.

Outputs

Output Name	Description	Data Type
`video`	The generated video. Contains an audio track when the `audio` option is enabled.	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): ff9fce554fa7aa5fc8729b5f84b2f8bf89e8e7772ce1c32b1307d0dc4882200c