Nodes/LingBot-Video Dense 1.3B FP8/LingBot TI2V Plaintext + Image + Qwen Encode
ComfyUI Node

LingBot TI2V Plaintext + Image + Qwen Encode

A ComfyUI node in LingBot Video with 8 inputs and 4 outputs.

By ALX-CODE·Created about a month ago·Updated 18 days ago· 8
LingBot TI2V Plaintext + Image + Qwen Encode
  • model
  • first_frame
  • conditioning
  • structured_json
  • expanded_caption
  • conditioned_first_frame
plaintext_promptThe subject begins from the supplied first frame, then moves naturally while preserving identity, clothing, lighting, and scene layout. Stable cinematic camera motion.
structured_json_override
duration_seconds3.0
negative_prompt
width640
height352
CategoryLingBot Video

Inputs (8)

NameTypeDefaultDescription
modelLINGBOT_MODEL
first_frameIMAGEThe first image in the batch is center-cropped to the selected video aspect ratio and fixed as frame 0.
plaintext_promptSTRINGThe subject begins from the supplied first frame, then moves naturally while preserving identity, clothing, lighting, and scene layout. Stable cinematic camera motion.Describe what should happen after the supplied first frame. Qwen sees the image during both rewrite stages.
structured_json_overrideSTRINGOptional advanced override. The supplied image is still used by Qwen-VL and as frame-0 conditioning.
duration_secondsFLOAT3.00.1–120
negative_promptSTRINGJSON only. Leave empty to use LingBot's vendored default negative prompt.
widthINT64016–4096
heightINT35216–4096

Outputs (4)

NameTypeDescription
conditioningLINGBOT_CONDITIONING
structured_jsonSTRING
expanded_captionSTRING
conditioned_first_frameIMAGE