ComfyUI Node: CogVideoX Model Loader
Category
CogVideoWrapper
Inputs
model
base_precision
- fp16
- fp32
- bf16
quantization
- disabled
- fp8_e4m3fn
- fp8_e4m3fn_fast
- torchao_fp8dq
- torchao_fp8dqrow
- torchao_int8dq
- torchao_fp6
load_device
- main_device
- offload_device
enable_sequential_cpu_offload BOOLEAN
block_edit TRANSFORMERBLOCKS
lora COGLORA
compile_args COMPILEARGS
attention_mode
- sdpa
- fused_sdpa
- sageattn
- fused_sageattn
- sageattn_qk_int8_pv_fp8_cuda
- sageattn_qk_int8_pv_fp16_cuda
- sageattn_qk_int8_pv_fp16_triton
- fused_sageattn_qk_int8_pv_fp8_cuda
- fused_sageattn_qk_int8_pv_fp16_cuda
- fused_sageattn_qk_int8_pv_fp16_triton
- comfy
Outputs
COGVIDEOMODEL
Extension: ComfyUI CogVideoX Wrapper
Diffusers wrapper for CogVideoX -models: a/https://github.com/THUDM/CogVideo
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