Nodes/Prompt Assistant/✨Video Caption (VLM)
ComfyUI Node

✨Video Caption (VLM)

Extract text prompt from video frames using Vision-Language Models

By yawiii·Created about a year ago·Updated 4 months ago· 2,119
✨Video Caption (VLM)
  • video_frames
  • video
  • caption_text
  • preview_frames
rule视频复刻与重构
custom_rulefalse
custom_rule_content
user_prompt
sampling_modeAuto (Uniform)
frame_count5
manual_indices
vlm_service智谱/glm-4.6V-Flash
ollama_auto_unloadtrue
seed0
Category✨Prompt Assistant

Inputs (12)

NameTypeDefaultDescription
ruleCOMBO视频复刻与重构Preset rule for video captioning
custom_ruleBOOLEANfalseEnable custom rule input
custom_rule_contentSTRINGCustom rule content, only used when Custom Rule is enabled
user_promptSTRINGEnter additional prompts here, sent with the rule
sampling_modeCOMBOAuto (Uniform)Auto: uniformly sample frames. Manual: specify indices via manual_indices
frame_countINT51–32Number of frames to sample (only for Auto mode)
manual_indicesSTRINGSpecific frame indices for Manual mode, e.g. 0,10,20 or 0-10
vlm_serviceCOMBO智谱/glm-4.6V-FlashSelect VLM Service
ollama_auto_unloadBOOLEANtrueAuto unload Ollama model after generation
seedINT00–18446744073709550000Controls randomness. Set to non-fixed mode to force re-execution
video_framesoptIMAGEThe video frames to analyze (IMAGE batch)
videooptVIDEOCompatible with VIDEO type nodes (like VHS)

Outputs (2)

NameTypeDescription
caption_textSTRING
preview_framesIMAGE