WanVideo Tea Cache (native)
WanVideoTeaCacheKJPatch WanVideo model to use TeaCache. Speeds up inference by caching the output and applying it instead of doing the step. Best results are achieved by choosing the appropriate coefficients for the model. Early steps should never be skipped, with too aggressive values this can happen and the motion suffers. Starting later can help with that too. When NOT using coefficients, the threshold value should be about 10 times smaller than the value used with coefficients. Official recommended values https://github.com/ali-vilab/TeaCache/tree/main/TeaCache4Wan2.1
Example
{
"class_type": "WanVideoTeaCacheKJ",
"inputs": {
"model": [
"node_id",
0
],
"rel_l1_thresh": 0.275,
"start_percent": 0.1,
"end_percent": 1,
"cache_device": "offload_device",
"coefficients": "i2v_480"
}
}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 | MODEL | required | - | - |
rel_l1_thresh? | FLOAT | required | min: 0, max: 10, step: 0.001 | 0.275 |
start_percent? | FLOAT | required | min: 0, max: 1, step: 0.01 | 0.1 |
end_percent? | FLOAT | required | min: 0, max: 1, step: 0.01 | 1 |
cache_device? | ENUM2 options
| required | - | "offload_device" |
coefficients? | ENUM5 options
| required | - | "i2v_480" |
Outputs
| Index | Name | Type | Is List | Connection Reference |
|---|---|---|---|---|
0 | model | MODEL | 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 WanVideoTeaCacheKJ node in your workflow, and output_index is the index from the table above.
Example
If this node has ID "5" in your workflow:
model (MODEL):["5", 0]