Nodes/Eric's Prompt Enhancers for ComfyUI/Image-to-Video Prompt Expander
ComfyUI Node

Image-to-Video Prompt Expander

A ComfyUI node in Eric Prompt Enhancers with 20 inputs and 4 outputs.

By EricRollei·Created 10 months ago·Updated 8 months ago· 38
Image-to-Video Prompt Expander
  • image
  • positive_prompt
  • negative_prompt
  • image_description
  • status
motion_descriptionslowly turns head and smiles at camera
presetcinematic
expansion_tierenhanced
reference_moderecreate_exact
use_vision_modeltrue
vision_backendlm_studio
vision_endpointhttp://localhost:1234/v1
expansion_backendlm_studio
expansion_endpointhttp://localhost:1234/v1
temperature0.7
camera_movementauto
shot_sizeauto
motion_speedauto
lighting_typeauto
time_of_daymaintain current
positive_keywords
negative_keywords
save_to_filefalse
filename_baseimg2vid_prompt
CategoryEric Prompt Enhancers

Inputs (20)

NameTypeDefaultDescription
imageIMAGE
motion_descriptionSTRINGslowly turns head and smiles at camera
presetCOMBOcinematic7 options: custom, cinematic, surreal, action, stylized, noir, +1
expansion_tierCOMBOenhanced5 options: auto, basic, enhanced, advanced, cinematic
reference_modeCOMBOrecreate_exactrecreate_exact: Keep exact character, outfit, lighting - animate this style_transfer: Match lighting/mood only, create new pose/scene character_remix: Use character but change outfit/setting face_only: Preserve face identity only, ignore background/lighting
use_vision_modelBOOLEANtrue
vision_backendCOMBOlm_studiolm_studio: Uses currently loaded model in LM Studio ollama: Uses currently loaded model in Ollama qwen3_vl: Auto-detects local Qwen3-VL model (no API server needed)
vision_endpointSTRINGhttp://localhost:1234/v1lm_studio/ollama: API endpoint URL qwen3_vl: Leave default, or specify custom model path like 'A:\path\to\model'
expansion_backendCOMBOlm_studiolm_studio: Uses currently loaded model in LM Studio ollama: Uses currently loaded model in Ollama qwen3_vl: Auto-detects local Qwen3-VL model (no API server needed)
expansion_endpointSTRINGhttp://localhost:1234/v1lm_studio/ollama: API endpoint URL qwen3_vl: Leave default, or specify custom model path like 'A:\path\to\model'
temperatureFLOAT0.70.1–2
camera_movementCOMBOauto15 options: auto, none, static shot, camera pushes in, dolly in, camera pulls back, +9
shot_sizeCOMBOauto8 options: auto, none, extreme close-up shot, close-up shot, medium close-up shot, medium shot, +2
motion_speedCOMBOauto6 options: auto, very slow, slow, normal, fast, very fast
lighting_typeCOMBOauto7 options: auto, none, soft lighting, hard lighting, edge lighting, rim lighting, +1
time_of_dayCOMBOmaintain current7 options: auto, none, maintain current, sunrise, daytime, sunset, +1
positive_keywordsSTRING
negative_keywordsSTRING
save_to_fileBOOLEANfalse
filename_baseSTRINGimg2vid_prompt

Outputs (4)

NameTypeDescription
positive_promptSTRING
negative_promptSTRING
image_descriptionSTRING
statusSTRING