ComfyUI Node: HyperLoRA Config

Authored by bytedance

Created

Updated

412 stars

Category

HyperLoRA

Inputs

image_processor
  • Not found!
image_encoder
  • Not found!
resampler.dim INT
resampler.dim_head INT
resampler.heads INT
resampler.depth INT
resampler.ff_mult INT
encoder_types
  • clip
  • arcface
  • clip + arcface
face_analyzer
  • Not found!
id_embed_dim INT
num_id_tokens INT
hyper_dim INT
lora_rank INT
has_base_lora BOOLEAN

Outputs

HYPER_LORA_CONFIG

Extension: ComfyUI-HyperLoRA

Official implementation in ComfyUI of CVPR 2025 paper 'HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis'

Authored by bytedance

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