Wan Text to Video

api node/video/Wan

WanTextToVideoApi

Generates a video based on a text prompt.

Example

JSON Example

{
  "class_type": "WanTextToVideoApi",
  "inputs": {
    "model": "wan2.6-t2v",
    "prompt": ""
  }
}

This example shows required inputs only. Connection values like ["node_id", 0] should reference actual node IDs from your workflow.

Inputs

Name	Type	Status	Constraints	Default
model?	COMBO	required	-	"wan2.6-t2v"
prompt?	STRING	required	-	""
negative_prompt?	STRING	optional	-	""
size	COMBO	optional	-	"720p: 1:1 (960x960)"
duration?	INT	optional	min: 5, max: 15, step: 5	5
audio?	AUDIO	optional	-	-
seed?	INT	optional	min: 0, max: 2147483647, step: 1	0
generate_audio?	BOOLEAN	optional	-	false
prompt_extend?	BOOLEAN	optional	-	true
watermark?	BOOLEAN	optional	-	true
shot_type?	COMBO	optional	-	-

Outputs

Index	Name	Type	Is List	Connection Reference
0	VIDEO	VIDEO	No	["{node_id}", 0]

How to connect to these outputs

To connect another node's input to an output from this node, use the connection reference format:

["node_id", output_index]

Where node_id is the ID of this WanTextToVideoApi node in your workflow, and output_index is the index from the table above.

Example

If this node has ID "5" in your workflow:

• VIDEO (VIDEO): ["5", 0]

Package: comfyui-api-nodes