ComfyUI Node: HunyuanVideo Model Loader
Category
HunyuanVideoWrapper
Inputs
model
base_precision
- fp32
- bf16
quantization
- disabled
- fp8_e4m3fn
- fp8_e4m3fn_fast
- fp8_e5m2
- fp8_scaled
- torchao_fp8dq
- torchao_fp8dqrow
- torchao_int8dq
- torchao_fp6
- torchao_int4
- torchao_int8
load_device
- main_device
- offload_device
attention_mode
- sdpa
- flash_attn_varlen
- sageattn
- sageattn_varlen
- comfy
compile_args COMPILEARGS
block_swap_args BLOCKSWAPARGS
lora HYVIDLORA
auto_cpu_offload BOOLEAN
upcast_rope BOOLEAN
Outputs
HYVIDEOMODEL
Extension: ComfyUI-HunyuanVideoWrapper
ComfyUI diffusers wrapper nodes for a/HunyuanVideo
Authored by kijai
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