Nodes/ComfyUI-WepeNerd/Image Captioner (Advanced)
ComfyUI Node

Image Captioner (Advanced)

A ComfyUI node in WepeNerd/Local AI/Advanced with 13 inputs and 1 output.

By WepeNerd·Created 4 months ago·Updated 2 days ago· 0
Image Captioner (Advanced)
  • config
  • image
  • caption
instructionDescribe this image accurately and in detail.
max_tokens512
temperature0.20
seed0
caption_style
reasoning_effortnone
system_prompt_override
caption_prefix
banned_phrases
image_max_edge1024
jpeg_quality90
CategoryWepeNerd/Local AI/Advanced

Inputs (13)

NameTypeDefaultDescription
configGGUF_LLM_CONFIG
imageIMAGE
instructionSTRINGDescribe this image accurately and in detail.
max_tokensINT5121–4096
temperatureFLOAT0.200–2
seedINT00–18446744073709550000
caption_styleCOMBO6 options: dataset_natural, detailed_visual, short, booru_tags, motion_camera, custom
reasoning_effortCOMBOnone5 options: default, none, low, medium, high
system_prompt_overrideoptSTRING
caption_prefixoptSTRING
banned_phrasesoptSTRING
image_max_edgeoptINT102464–4096
jpeg_qualityoptINT901–100

Outputs (1)

NameTypeDescription
captionSTRING