Nodes/comfyui-fvmtools/Scene Describe (LM Studio)
ComfyUI Node

Scene Describe (LM Studio)

Describe the photograph once and feed both the text proposer (`scene_hint`) and the caption builder. Without it the proposer invents signage for the wrong kind of place, or falls back on transcribing the nonsense already in the picture.

By ping1979ping·Created 6 months ago·Updated 2 days ago· 1
Scene Describe (LM Studio)
  • image
  • summary
  • background
  • setting
  • report
◄base_urlhttp://localhost:1234/v1►
◄model_idqwen3-8b-vl-instruct-abliterated►
◄enabledtrue►
◄temperature0.00►
◄timeout180►
◄fallback_summary►
◄fallback_background►
◄fallback_setting►
CategoryFVMtools/signs

Inputs (9)

NameTypeDefaultDescription
imageIMAGEThe picture to read.
base_urlSTRINGhttp://localhost:1234/v1LM Studio, OpenAI-compatible.
model_idSTRINGqwen3-8b-vl-instruct-abliteratedName it. 'Whatever is loaded' is not a default, it is a silent failure: LM Studio lists models it has not loaded, the call returns nothing, and the graph carries on with an empty description. Must be a VISION model.
enabledBOOLEANtrueOff: pass the fallbacks through unchanged, so the effect of the description can be measured.
temperatureFLOAT0.000–10.0. Measured over a hundred runs elsewhere in this project: at 0.2 and above the model invents one-off answers that never repeat.
timeoutINT18010–900—
fallback_summaryoptSTRING—
fallback_backgroundoptSTRING—
fallback_settingoptSTRING—

Outputs (4)

NameTypeDescription
summarySTRING—
backgroundSTRING—
settingSTRING—
reportSTRING—