All tutorials

Video & audio

Create a live-arena character fight with MiniMax H3

Prepare the source assets, follow the supplied generation workflow, and inspect the result frame by frame before exporting.

Guide
TUT-053
Time
58 min
Level
Intermediate
Reviewed

Adapted from TUT-053, dated 2026-08-03.

What you'll make

A checked final video that follows the source workflow and is ready for export.

Create a live-arena character fight with MiniMax H3

Who this is for

Creators, marketers, founders, and small teams producing short AI-assisted videos from source media.

Step by step

Run the workflow

  1. 01

    Review the workflow

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. complete workflow I used to create this video.
    Source example for create a live-arena character fight with minimax h3.
    Use this visual to confirm the expected setup or result.
    Source example for create a live-arena character fight with minimax h3.
    Use this visual to confirm the expected setup or result.
    Common failure modes
    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
  2. 02

    Generate the source images

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. We'll begin by creating the images.
    2. Click "Create image" in the top-left navigation bar.
    3. Select the "Seedream 5.0 Pro" model.
    Source example for review the workflow.
    Use this visual to confirm the expected setup or result.
    Source example for review the workflow.
    Use this visual to confirm the expected setup or result.
    Common failure modes
    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
  3. 03

    First Image

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. First, upload your image.
    2. Download my reference image below, then upload it.
    3. Paste the prompt below:
    4. Replace the face of the man in the crowd with the image of my selfie
    Upload interface used for generate the source images.
    Check the selected files and their order before continuing.
    Upload interface used for generate the source images.
    Check the selected files and their order before continuing.
    Common failure modes
    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
  4. 04

    Second Image

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Download my reference image below
    Source example for first image.
    Use this visual to confirm the expected setup or result.
    Common failure modes
    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
  5. 05

    Open the video generator

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. With your assets ready, it's time to create your reel!
    2. I am using Higgsfield for my Seedance 2.0:
    3. Click "Video" in the top-left navigation bar and select Create Video
    4. Select the "Seedance 2.0" model.
    Source example for second image.
    Use this visual to confirm the expected setup or result.
    Common failure modes
    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.
  6. 06

    Upload the reference assets

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Click "Upload Media".
    2. Upload both the images and paste in the prompt:
    3. Adjust the video duration, aspect ratio, and resolution accordingly to your recorded footage.
    Upload interface used for open the video generator.
    Check the selected files and their order before continuing.
    Upload interface used for open the video generator.
    Check the selected files and their order before continuing.
    Upload interface used for open the video generator.
    Check the selected files and their order before continuing.
    Common failure modes
    • The generated scene changes the person, camera, room, product, or timing beyond the requested effect.
    • Fast motion hides face, hand, clothing, text, or continuity errors that become visible when the clip is paused.

Before you use it

Final checks

  • Check the full result for changed people, products, text, timing, or layout.
  • Confirm the tool, model, controls, and cost before generating.
  • Keep private or unreleased material out of third-party tools.

Share your work

Made it? Show me.

Post your finished result on Instagram and tag @terencesia. I'll share a few standout results with the community.

Tag @terencesia on Instagram (opens in a new tab)

Next step

Run one low-cost test, record the first visible failure, and revise only the instruction or source asset tied to that problem.

Back to the tutorial library

Sources

What this guide relies on