FaceDetailer

ImpactPack/Simple

This node enhances details by automatically detecting specific objects in the input image using detection models (bbox, segm, sam) and regenerating the image by enlarging the detected area based on the guide size. Although this node is specialized to simplify the commonly used facial detail enhancement workflow, it can also be used for various automatic inpainting purposes depending on the detection model.

Pack: ComfyUI Impact Pack

custom_nodes.ComfyUI-Impact-Pack

Inputs (39)

Name	Type	Required
image	IMAGE	required
model	MODEL	required
clip	CLIP	required
vae	VAE	required
guide_size	FLOAT	required
guide_size_for	BOOLEAN	required
max_size	FLOAT	required
seed	INT	required
steps	INT	required
cfg	FLOAT	required
sampler_name	COMBO	required
scheduler	COMBO	required
positive	CONDITIONING	required
negative	CONDITIONING	required
denoise	FLOAT	required
feather	INT	required
noise_mask	BOOLEAN	required
force_inpaint	BOOLEAN	required
bbox_threshold	FLOAT	required
bbox_dilation	INT	required
bbox_crop_factor	FLOAT	required
sam_detection_hint	COMBO	required
sam_dilation	INT	required
sam_threshold	FLOAT	required
sam_bbox_expansion	INT	required
sam_mask_hint_threshold	FLOAT	required
sam_mask_hint_use_negative	COMBO	required
drop_size	INT	required
bbox_detector	BBOX_DETECTOR	required
wildcard	STRING	required
cycle	INT	required
sam_model_opt	SAM_MODEL	optional
segm_detector_opt	SEGM_DETECTOR	optional
detailer_hook	DETAILER_HOOK	optional
inpaint_model	BOOLEAN	optional
noise_mask_feather	INT	optional
scheduler_func_opt	SCHEDULER_FUNC	optional
tiled_encode	BOOLEAN	optional
tiled_decode	BOOLEAN	optional

Outputs (6)

Name	Type
image	IMAGE
cropped_refined	IMAGE
cropped_enhanced_alpha	IMAGE
mask	MASK
detailer_pipe	DETAILER_PIPE
cnet_images	IMAGE