FlowWall

Video generation node

Basic configuration

Purpose: Generate video based on text, image, video or audio input.

01

Add video node.

02

Different models support different reference methods and parameters. For details, please refer to03.2 Video model and common parameters

Models and parameters of video nodes
  1. 01Video model: Click to switch to generate model
  2. 02Reference mode: select all-purpose reference or first and last frame modes
  3. 03Aspect ratio: set landscape, portrait or square
  4. 04Resolution: Set the output resolution
  5. 05Duration: Set the length of the generated video
  6. 06Generation quantity: Set how many videos to generate at one time
  7. 07Audio switch: turn on or off synchronized audio
03

ChooseAll-round referencemode.

Connection and generation of universal reference patterns
  1. 01Reference material: connect pictures, videos or audio
  2. 02Prompt word: Enter the picture and action you want to generate
  3. 03Generate parameters: set model, scale, duration, etc.
  4. 04Run: Start generating video
04

ChooseFirst and last framesmode.

Connection method of first and last frame mode
  1. 01First frame: Connect the beginning of the video
  2. 02End frame: Connect the video ending screen
  3. DescriptionConnect the first and last frame pictures, and then select the first and last frame mode.
Video model parameter matrix
DATA TABLEVideo model parameters
modelMaterial reference formWhat is suitable for generatingresolutiondurationThe quantity you can choose to generate at one time
MiniMax H3Universal reference, first and last framesIt supports all-round reference and is cost-effective, suitable for videos that require a variety of reference materials.720p4–15 seconds1
Gemini Omni FlashAll-purpose reference, you can specify the first frameEmphasis on physical perception and consistency, suitable for the use of picture or video reference generation.720p4–10 seconds1
Seedance 2.5All-round reference, first and last frames, intelligent editing (can partially edit existing videos), super long video (can generate 180s long video at one time)The latest official multi-modal Video generation, suitable for scenarios where you want to get a complete video quickly.480p、720p、1K、4K4–30 seconds1–4
Seedance 2.0Universal reference, first and last framesSupports picture, video and audio reference, suitable for multi-modal material creation.720p、1080p、4K4–15 seconds1–4
Seedance 2.0 (fast version)Universal reference, first and last framesFast multimodal Video generation up to 720p for quick previews.720p4–15 seconds1–4
SeedanceLite2Universal reference, first and last framesClose to the native effect of Seedance 2, supporting up to 4K, suitable for cost control.720p、1080p、4K4–15 seconds1–4
SeedanceLite2 FastUniversal reference, first and last framesFast output to 720p for low-cost, fast previews.720p4–15 seconds1–4
Seedance 1.0 Pro FastOnly one picture can be uploaded as the first frameThe generation speed is fast, the movement is smooth, the picture is exquisite, and it is suitable for quick preview.720p、1080p2–12 seconds1–4