MiniMax H3 · Text to Video

ABOUT THE WORKFLOW

Turn text into video
Type what you want to see and get back a video clip with sound. The model generates the picture and the audio together from the same prompt, so dialogue, effects, and ambient sound land with the action. No footage or reference needed.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• MiniMax H3 (Hailuo 3.0) by MiniMax. A multimodal video model that generates up to 15 seconds of native 2K video with synchronized stereo audio in a single pass.

HOW IT WORKS

Step 1. Write your prompt
Describe the scene: subjects, actions, setting, camera movement, and mood. The model builds both the picture and the sound from it.
Works great with: cinematic scenes · ads · character moments · b-roll

Step 2. Hit run
The model generates the clip, with the audio timed to the action.

Step 3. Download your video
You get a native 2K clip with synchronized sound. Preview it, then download.
Ready for: editing timelines · social · ads

First time? Leave every setting as-is. The defaults (5 seconds · 16:9) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard use (most people) — 5 seconds, 16:9. The right starting point for almost everyone.

• Want a longer scene — set the duration to 10 or 15 seconds for a longer clip in one generation.

• Making vertical content — switch the aspect ratio to 9:16 for phones and short-form feeds.

• Making a square post — switch to 1:1 for feeds that favour square video.

• Want specific dialogue or sound — describe it in the prompt, since the audio is generated from the same text.

• Not getting the motion you want — name the camera move and the action clearly, like "slow dolly in as she turns to face the window."

Prompt: Describe the shot like a director. Name the subject, the action, the setting, the camera move, and the mood, and add any dialogue or sound you want. "A chef plates a dish in a warm kitchen, slow push-in, soft jazz and a gentle sizzle in the background" beats "a cooking video." The clearer the scene, the tighter the picture and sound come back.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🎬 Ad & Promo Clips
Generate short product or brand spots with sound from a written brief.

📱 Social Video
Make vertical clips for short-form feeds without a camera or a shoot.

🎞️ B-roll & Establishing Shots
Fill an edit with a specific scene you cannot shoot yourself.

🎨 Concept & Pitch
Visualise a scene with motion and sound to sell an idea before production.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Prompts that name subject, action, and camera

• A single, clear scene per clip

• Sound and dialogue described in the prompt

• A defined mood or lighting

⚠️ May produce softer results

• Vague, one-word prompts

• Many unrelated actions in one clip

• Long passages of on-screen text or logos

• Contradictory camera or motion notes

FAQ

What is MiniMax H3 (Hailuo 3.0)?
MiniMax H3, also called Hailuo 3.0, is MiniMax's flagship multimodal video model, launched in July 2026. It generates native 2K video at 24 frames per second, with clips up to 15 seconds, and produces synchronized stereo audio in the same pass as the picture. This workflow runs it in text-to-video mode.

Does the generated video come with sound?
Yes. Dialogue, sound effects, and ambient atmosphere are generated alongside the video in a single pass and timed to the on-screen action. That means the clip comes back with a matching audio track rather than a silent render you have to score later.

What resolution and clip length can I get?
The model outputs native 2K at 24 frames per second. You can choose a duration of 5, 10, or 15 seconds per generation, and set the aspect ratio to 16:9, 9:16, 1:1, or other supported shapes to match where the video is going.

How is MiniMax H3 different from Hailuo 2.3?
Hailuo 2.3 tops out around 1080p and roughly 10 seconds, without built-in audio. MiniMax H3 moves to native 2K, stretches clips to 15 seconds, and adds synchronized stereo sound generated with the picture, so it fits short-form scenes that need audio out of the box.

Can I use MiniMax H3 videos commercially?
MiniMax H3 is a proprietary model accessed through an API, so commercial use is governed by MiniMax's terms rather than an open license. Commercial use is generally supported for ads and content, but review MiniMax's current terms and make sure you have the rights to anything you describe or reference.

How to run MiniMax H3 online?
You can run MiniMax H3 online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, type a prompt, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A creator generates a clip and likes it. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it?
Type a prompt and run it. You get a 2K video with sound.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.