MiniMax H3 · Image to Video

ABOUT THE WORKFLOW

Bring a photo to life
Upload a picture and describe the motion you want, and the model animates it into a short clip. Add optional references to guide the look, the motion, or the sound. It reads your image, your prompt, and any references together, then generates a clip at up to native 2K.

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 reads your image, prompt, and any references together and generates a short clip at up to native 2K.

HOW IT WORKS

Step 1. Upload your image
The picture you want brought to life.
Works great with: portraits · characters · products · scenes

Step 2. Describe the motion
Say what should move and how, plus the camera, lighting, and mood, like "she turns to the window as the camera slowly pushes in."

Step 3. Add references (optional)
Bring in up to nine images, three video clips, and three audio clips to guide the look, motion, or sound.

Step 4. Hit run and download
The model animates your image into a short clip at up to 2K. The file saved here is picture only.
Ready for: editing timelines · social · ads

First time? Leave every setting as-is. The defaults (5 seconds · 16:9 · 30 fps) 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, 30 fps. The right starting point for almost everyone.

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

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

• Keep a character or product consistent — add reference images so the same face, outfit, or object carries into the motion.

• Guide the motion or style — add a reference video clip so the movement or look follows footage you already have.

• Composite two images into one scene — connect a subject image and a scene image, then describe how they combine, like placing the person into the location.

Prompt: Describe what moves and how, then the camera, lighting, and mood. "The man walks along the garden path toward the cottage, hands in his pockets, then glances at the camera with a small smile, slow push-in" beats "make it move." When you add references, say what each one is for, like the person to keep or the scene to place them in.

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

🎞️ Bring Photos to Life
Animate a still portrait or product shot into a short moving clip.

🧩 Composite into Motion
Place a person or product from one image into a scene from another, then set it moving.

🎬 Character Consistency
Carry a face, outfit, or product across a clip with reference images.

📱 Social & Ads
Turn a key image into short-form video for feeds and campaigns.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• A clear, well-lit main image

• Prompts that name the motion and camera

• Reference images for a face, outfit, or scene

• A single subject to animate

⚠️ May produce softer results

• Cluttered or low-resolution source images

• Vague motion like "make it move"

• Too many conflicting references

• Extreme or physically impossible motion

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 reads text, images, video, and audio together and generates native 2K video at 24 frames per second, with clips up to 15 seconds. This workflow runs it in image-to-video mode.

How does image-to-video work here?
You upload a main image and write a prompt describing the motion, camera, and mood. The model animates your picture into a short clip that follows the prompt. You can also add references to steer the look, motion, or sound before it generates.

What references can I add, and what do they do?
You can add up to nine images, three video clips, and three audio clips. Images lock in a face, object, style, or scene, video clips guide motion or look, and audio clips guide voice or sound. For example, you can put a person from one image into a scene from another and describe how they move through it.

Does the saved video have sound?
MiniMax H3 generates audio along with the picture, but the file this workflow saves is picture only. If you need the video with its synchronised sound, use a MiniMax H3 workflow that keeps the audio track in the saved file.

What resolution and clip length can I get?
The model outputs up to native 2K at 24 frames per second. You can set the duration to 5, 10, or 15 seconds per generation, and choose 16:9, 9:16, or another supported aspect ratio to match your target.

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 the image and any references you upload.

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, upload an image, describe the motion, 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 animates an image 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?
Upload an image, describe the motion, and run it. You get a short 2K clip.

→ Launch Workflow, Free

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