MinimaxHailuo03FirstLastFrameNode - ComfyUI Built-in Node Documentation

This node generates a video from a first frame image and, optionally, a last frame image using MiniMax H3 models.

This node generates a video from a first frame image and, optionally, a last frame image using MiniMax H3 models. The model selector changes which generation settings and constraints apply, and the aspect ratio of the generated video follows the supplied images.

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
model	Model to use for video generation. Selecting a model reveals its model-specific settings below.	DYNAMIC_COMBO	Yes	”MiniMax H3" "MiniMax H3 Max" "MiniMax H3 Max Turbo”
first_frame	First frame image for the video. The generated video follows the aspect ratio of this image.	IMAGE	Yes	-
last_frame	Optional last frame image for the video. When provided, the video is generated from the first frame toward this last frame.	IMAGE	No	-
seed	Random seed. The same request with the same seed gives similar, but not guaranteed identical, results. Includes a “control after generate” option. Default: 42.	INT	Yes	0 to 4294967295
watermark	Whether to add an AIGC watermark to the video. This is an advanced parameter. Only supported by the MiniMax H3 model. Default: False.	BOOLEAN	Yes	True False

MiniMax H3 Inputs

These settings are shown when MiniMax H3 is selected in the model selector.

Parameter	Description	Data Type	Required	Range
prompt	Text prompt for video generation. Must contain at least one non-whitespace character.	STRING	Yes	Multiline text
resolution	Resolution of the output video.	COMBO	Yes	”768P" "2K”
duration	Duration of the output video in seconds. Default: 5.	INT	Yes	4 to 15

MiniMax H3 Max and MiniMax H3 Max Turbo Inputs

These settings are shown when either MiniMax H3 Max or MiniMax H3 Max Turbo is selected in the model selector. Both models expose the same settings.

Parameter	Description	Data Type	Required	Range
prompt	Text prompt for video generation. Must not be empty or whitespace-only, and is limited to 50,000 characters.	STRING	Yes	Multiline text
resolution	Resolution of the output video. Default: 768P.	COMBO	Yes	”480P" "768P”
duration	Duration of the output video in seconds. Default: 5.	INT	Yes	5 to 15
prompt_expansion_mode	How much effort is spent rewriting the prompt before generation. Default: balanced.	COMBO	Yes	”balanced" "quality”

Notes on constraints:

• The prompt must contain text: empty or whitespace-only prompts are rejected.
• Any supplied frame image must be at least 256 pixels wide and 256 pixels tall, with a width-to-height aspect ratio between 0.4 and 2.5 (approximately 2:5 to 5:2). This requirement applies to first_frame and, when provided, last_frame.
• When last_frame is omitted, the video is generated from the first frame only.
• The output video follows the aspect ratio of the supplied images.
• watermark is only supported by MiniMax H3. Enabling it with MiniMax H3 Max or MiniMax H3 Max Turbo raises an error.
• Duration ranges from 4 to 15 seconds for MiniMax H3 and from 5 to 15 seconds for MiniMax H3 Max and MiniMax H3 Max Turbo.

Outputs

Output Name	Description	Data Type
video	The generated video created from the first frame and optional last frame using the selected MiniMax H3 model.	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): 6eaf895e6e9e46b9a1efb1dd13e951040e12e865cc73d7741ab7546f5f8f9ec0