ComfyUI Node: Eric Reference Describer (VL→Text)
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
Eric/VisualResearch
Inputs
grounded_prompt STRING
ref_image_1 IMAGE
vl_api_url STRING
ref_image_2 IMAGE
ref_image_3 IMAGE
ref_image_4 IMAGE
model_name STRING
description_focus
- auto
- full_scene
- subject_appearance
- clothing_and_style
- setting_and_environment
synthesis_mode
- synthesize
- append
max_image_dim INT
Outputs
STRING
STRING
Extension: Eric Visual Research
Agentic web research nodes for ComfyUI — grounded prompt generation and VL reference description
Authored by EricRollei
Looking for a different node?
More nodes in Eric Visual Research
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.