ComfyUI Node
Halo-TeaCache v1.0.0 (AMD LTX2)
A ComfyUI node in Halo-TeaCache with 4 inputs and 1 output.
Halo-TeaCache v1.0.0 (AMD LTX2)
- model
- model
◄rel_l1_thresh0.20►
◄start_percent0.15►
◄end_percent1.00►
CategoryHalo-TeaCache
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| model | MODEL | The LTX2 diffusion model to accelerate. | |
| rel_l1_thresh | FLOAT | 0.200–2 | Cache threshold - higher = more skipping (faster but lower quality). 0 = disabled. Try 0.15-0.30. |
| start_percent | FLOAT | 0.150–1 | Start caching after this % of steps (early steps need full compute). |
| end_percent | FLOAT | 1.000–1 | Stop caching after this % of steps. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |