ComfyUI Node: Apply PuLID Flux

Authored by sipie800

Created

Updated

182 stars

Category

pulid

Inputs

model MODEL
pulid_flux PULIDFLUX
eva_clip EVA_CLIP
face_analysis FACEANALYSIS
image IMAGE
weight FLOAT
start_at FLOAT
end_at FLOAT
fusion
  • mean
  • concat
  • max
  • norm_id
  • max_token
  • auto_weight
  • train_weight
fusion_weight_max FLOAT
fusion_weight_min FLOAT
train_step INT
use_gray BOOLEAN
attn_mask MASK
prior_image IMAGE

Outputs

MODEL

Extension: ComfyUI-PuLID-Flux-Enhanced

adapted from a/https://github.com/balazik/ComfyUI-PuLID-Flux. common fusion methods for multi-image input, some further experimental fusion methods, switch between using gray image (official) and rgb.,

Authored by sipie800

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