🖼️ Local Image Analysis (GGUF)

VisionLanguageNode

🤖 GGUF-VLM/🖼️ Vision Modelsoutput node

Pack: Qwen2.5-VL GGUF Nodes

custom_nodes.ComfyUI-GGUF-VLM

Inputs (10)

Name	Type	Required
model	VISION_MODEL	required
prompt	STRING	required
max_tokens	INT	required
temperature	FLOAT	required
top_p	FLOAT	required
top_k	INT	required
seed	INT	required
image	IMAGE	optional
video	IMAGE	optional
system_prompt	STRING	optional

Outputs (1)

Name	Type
context	STRING