Nodes/ERPK Collection/Kling O3 Image-to-Video
ComfyUI Node

Kling O3 Image-to-Video

A ComfyUI node in ERPK/WaveSpeedAI with 13 inputs and 1 output.

By eRepublik-Labs·Created 10 months ago·Updated about a month ago· 0
Kling O3 Image-to-Video
  • image
  • end_image
  • client
  • video_url
modelKling O3
prompt
image_url
duration5
seed-1
end_image_url
soundfalse
shot_typeintelligent
multi_prompt
element_list
CategoryERPK/WaveSpeedAI

Inputs (13)

NameTypeDefaultDescription
modelCOMBOKling O3Model variant: Kling O3 (standard) or Kling O3 Pro (adds element_list)
promptSTRINGText description of motion, camera movement, and action
image_urlSTRINGStarting image URL (use WaveSpeed Upload Image to produce one). Fallback when the IMAGE input is not connected.
imageoptIMAGEStarting image as a ComfyUI IMAGE tensor. Preferred — takes precedence over `image_url` when connected.
end_imageoptIMAGEOptional end-frame image as a ComfyUI IMAGE tensor for guided transitions. Preferred — takes precedence over `end_image_url` when connected.
clientoptWAVESPEED_AI_API_CLIENTWaveSpeed API client (optional if API key is configured in Settings)
durationoptINT53–15Video duration in seconds. Std accepts 3-15; Pro accepts 5 or 10.
seedoptINT-1-1–2147483647Retained for workflow compatibility; the O3 API does not accept a seed parameter.
end_image_urloptSTRINGEnd-frame image URL for guided transitions. Fallback when the end_image IMAGE input is not connected.
soundoptBOOLEANfalseEnable synchronized audio generation (raises base cost)
shot_typeoptCOMBOintelligentShot composition mode: 'intelligent' (auto) or 'customize' (manual)
multi_promptoptSTRINGJSON array of scene-segmented prompts guiding scene transitions
element_listoptSTRINGPro only: JSON array of Kling Elements IDs to lock for visual consistency

Outputs (1)

NameTypeDescription
video_urlSTRING