ComfyUI Node: LayerUtility: ImageAutoCrop

Authored by chflame163

Created 9 months ago

Updated 17 days ago

1267 stars

Category

😺dzNodes/LayerUtility

Inputs

image IMAGE

background_color STRING

aspect_ratio

• 1:1
• 3:2
• 4:3
• 16:9
• 2:3
• 3:4
• 9:16
• custom
• detect_mask

proportional_width INT

proportional_height INT

scale_to_longest_side BOOLEAN

longest_side INT

detect

• min_bounding_rect
• max_inscribed_rect
• mask_area

border_reserve INT

ultra_detail_range INT

matting_method

• RMBG 1.4
• SegmentAnything

sam_model

• sam_vit_h (2.56GB)
• sam_vit_l (1.25GB)
• sam_vit_b (375MB)
• sam_hq_vit_h (2.57GB)
• sam_hq_vit_l (1.25GB)
• sam_hq_vit_b (379MB)
• mobile_sam(39MB)

grounding_dino_model

• GroundingDINO_SwinT_OGC (694MB)
• GroundingDINO_SwinB (938MB)

sam_threshold FLOAT

sam_prompt STRING

Outputs

IMAGE

IMAGE

MASK

Extension: ComfyUI Layer Style

A set of nodes for ComfyUI it generate image like Adobe Photoshop's Layer Style. the Drop Shadow is first completed node, and follow-up work is in progress.

Authored by chflame163