ComfyUI Node: HuMo Audio Attention Control v4

Authored by ckinpdx

Created

Updated

1 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

WanVideoWrapper/HuMo

Inputs

model WANVIDEOMODEL
enable_audio_cross_attn BOOLEAN
audio_blocks
  • custom
  • early_0-5_structure
  • early_0-10_body
  • mid_6-24_lipsync
  • mid_10-25_gestures
  • late_25-39_texture
  • most_0-30_aggressive
  • all_0-39_maximum
audio_q_scale FLOAT
audio_k_scale FLOAT
audio_v_scale FLOAT
audio_o_scale FLOAT
enable_cross_attn BOOLEAN
cross_blocks
  • custom
  • early_0-5_structure
  • early_0-10_body
  • mid_6-24_lipsync
  • mid_10-25_gestures
  • late_25-39_texture
  • most_0-30_aggressive
  • all_0-39_maximum
cross_q_scale FLOAT
cross_k_scale FLOAT
cross_v_scale FLOAT
cross_o_scale FLOAT
enable_self_attn BOOLEAN
self_blocks
  • custom
  • early_0-5_structure
  • early_0-10_body
  • mid_6-24_lipsync
  • mid_10-25_gestures
  • late_25-39_texture
  • most_0-30_aggressive
  • all_0-39_maximum
self_q_scale FLOAT
self_k_scale FLOAT
self_v_scale FLOAT
self_o_scale FLOAT
audio_custom_range STRING
cross_custom_range STRING
self_custom_range STRING

Outputs

WANVIDEOMODEL

Extension: comfyui-humo-audio-motion

ComfyUI custom node for granular Q/K/V/O attention boosting in HuMo models. Provides 12 independent controls for fine-tuning audio-driven motion response.

Authored by ckinpdx

View Nodes

Looking for a different node?

More nodes in comfyui-humo-audio-motion

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more