ComfyUI Node: DreamWaltzG Stage One Trainer

Authored by gt732

Created

Updated

2 stars

Category

DreamWaltzG

Inputs

prompt STRING
iterations INT
train_resolution
  • 64,64
  • 64,128,256
  • 512,512
background_mode
  • gray
  • white
  • black
body_parts
  • hands
  • face
  • full
scene_type
  • canonical
  • dynamic
enable_fp16 BOOLEAN
enable_progressive_grid BOOLEAN
enable_sigma_guidance BOOLEAN

Outputs

STRING

IMAGE

Extension: ComfyUI-DreamWaltz-G

This repository contains custom ComfyUI nodes designed to integrate with a/DreamWaltz-G, a cutting-edge model for generating expressive 3D Gaussian avatars using skeleton-guided 2D diffusion.

Authored by gt732

View Nodes

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