ComfyUI Node: TeaCache
Category
TeaCache
Inputs
model MODEL
model_type
- flux
- flux-kontext
- ltxv
- lumina_2
- hunyuan_video
- hidream_i1_full
- hidream_i1_dev
- hidream_i1_fast
- wan2.1_t2v_1.3B
- wan2.1_t2v_14B
- wan2.1_i2v_480p_14B
- wan2.1_i2v_720p_14B
- wan2.1_t2v_1.3B_ret_mode
- wan2.1_t2v_14B_ret_mode
- wan2.1_i2v_480p_14B_ret_mode
- wan2.1_i2v_720p_14B_ret_mode
rel_l1_thresh FLOAT
start_percent FLOAT
end_percent FLOAT
cache_device
- cuda
- cpu
Outputs
MODEL
Extension: ComfyUI-TeaCache
Unofficial implementation of ali-vilab/TeaCache for ComfyUI
Authored by welltop-cn
Run ComfyUI workflows in the Cloud!
No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues
Learn more