MinimaxHailuo03MaxCameraControlNode - ComfyUI Built-in Node Documentation

This node generates a video that starts from a still image and moves the camera to a new angle and distance around the subject.

This node generates a video that starts from a still image and moves the camera to a new angle and distance around the subject. Azimuth, elevation and distance describe where the camera ends up; the first frame stays exactly as supplied. When no prompt is given the scene stays frozen and only the camera moves.

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
model	Model to use for video generation.	DYNAMIC_COMBO	Yes	”MiniMax H3 Max”

MiniMax H3 Max Inputs

Parameter	Description	Data Type	Required	Range
image	First frame of the video, at least 256x256 pixels. The aspect ratio must be between 0.4 and 2.5.	IMAGE	Yes	Single image
camera_info	Optional end camera, for example from Create Camera Info or Compose Camera Angle Prompt, with the image as the front view. When connected it sets the azimuth and elevation.	LOAD3D_CAMERA	No	Camera info
prompt	Optional. When empty, the scene stays frozen and only the camera moves.	STRING	Yes	0 to 50000 characters
azimuth	Horizontal orbit around the subject at the end of the video, in degrees from the image (default: 90). Positive values move the camera to the right, so the subject turns toward the left of the frame. It is a target: a 90 degree orbit often lands between 30 and 90 degrees. Ignored when camera_info is connected.	INT	Yes	-360 to 360
elevation	Vertical camera angle at the end of the video, in degrees (default: 0). Positive values look down from above, negative values look up from below. Ignored when camera_info is connected.	INT	Yes	-90 to 90
distance	Camera distance at the end of the video relative to the image: 1 keeps it, below 1 moves closer, above 1 pulls back (default: 1.0).	FLOAT	Yes	0.1 to 10.0
duration	Duration of the output video in seconds (default: 5).	INT	Yes	1 to 15
resolution	Resolution of the output video (default: “768P”).	COMBO	Yes	”480P" "768P" "1080P”
prompt_expansion_mode	How much effort is spent rewriting the prompt before generation (default: “balanced”).	COMBO	Yes	”disabled" "balanced" "quality”
seed	Random seed. The same request with the same seed gives similar, but not guaranteed identical, results (default: 42).	INT	Yes	0 to 4294967295

Outputs

Output Name	Description	Data Type
video	The generated video with the camera move applied.	VIDEO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

---

Source fingerprint (SHA-256): d9eed1a3ae91891b974bea39ea00101c0577cf5b204d4c701b13b232e0604153