Minimax H3 Controlnet Union

What you can set

• PromptRequired

  Text

  Describe the output video. The source video's motion and composition are carried over through the selected control. Refer to reference inputs as <Picture 1>..<P

• Reference audios

  Upload one or more audio files

  Optional reference audio URLs to guide audio generation. Refer to them in the prompt as <Audio 1>..<Audio 3>.

• Reference images

  Upload one or more images

  Optional reference image URLs, e.g. the character to animate or a target style. Refer to them in the prompt as <Picture 1>..<Picture 9>.

• VideoRequired

  Upload a video

  URL of the source video (up to 15 seconds are used). The control signal is extracted from it automatically and drives motion and composition; the output keeps i

• Control strength

  Number from 0 to 2

  How strongly the control signal constrains the output. Lower values give the prompt more freedom.

• Control type

  Choice

  What to keep from the source video: pose (body, hand and face motion), depth (spatial layout), canny (precise edges), soft_edge (softer outlines), lines (straig

  • pose (default)
  • depth
  • canny
  • soft_edge
  • lines
  • scribble
  • gray

• Generate audio

  On or off

  Whether to generate native audio. When set to false, the source video's audio track is preserved on the output instead.

• Resolution

  Choice

  Output video resolution. 768p is the model's native canvas; 480p is a faster, lower-cost tier; 540p is a mid tier at 1.5x the 480p price. 1080p is the highest-q

  • 480p (default)
  • 540p
  • 768p
  • 1080p

• Seed

  Number, repeats a result

  The random seed to use for the generation. A negative value means a random seed will be used.