[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [MiniMax H3 Image to Video LoRA](https://spiral.ai/integrations/opencode/minimax-h3-image-to-video-lora)

# How to Use MiniMax H3 Image to Video LoRA in opencode

MiniMax H3 Image to Video LoRA animates a still with trained customization for subject consistency. Compared with MiniMax H3 Image to Video, it adds LoRA support for a character or visual treatment.

|  |  |
| --- | --- |
| Model | MiniMax H3 Image to Video LoRA |
| Available through | fal |
| Category | Video |
| Price | `resolution`: 480P $0.08125, 768P $0.0975, 2K (default) $0.21125, 4K $0.26 per second. Billed on `duration`, default 5. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with MiniMax H3 Image to Video LoRA in opencode

- Animate the image I attach with MiniMax H3 Image to Video LoRA: slow push-in, leaves moving in the wind. Save the result in ./assets.
- Turn this product photo into a 5-second rotating shot with MiniMax H3 Image to Video LoRA.
- Bring this portrait to life with MiniMax H3 Image to Video LoRA: a subtle smile and a blink.
- Animate this illustration with MiniMax H3 Image to Video LoRA: clouds drifting, a slow camera pan to the right.
- Animate each of these five product photos with MiniMax H3 Image to Video LoRA and give me the clips in one list.

## How to set up MiniMax H3 Image to Video LoRA in opencode

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Leave out `--global` to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **Sign in**: Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, `/mcps` starts the same sign-in.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run MiniMax H3 Image to Video LoRA**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "minimax/h3/image-to-video/lora",
    "input": {
      "prompt": "The camera slowly pulls back from the scene, revealing the full landscape as clouds drift overhead and light shifts across the terrain.",
      "loras": [
        {
          "path": "https://huggingface.co/owner/repo/resolve/main/lora.safetensors"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: opencode finds MiniMax H3 Image to Video LoRA on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/opencode

## MiniMax H3 Image to Video LoRA tools and prices

- [MiniMax H3 Image to Video LoRA](https://spiral.ai/tools/fal/minimax/h3/image-to-video/lora) (fal): `resolution`: 480P $0.08125, 768P $0.0975, 2K (default) $0.21125, 4K $0.26 per second. Billed on `duration`, default 5.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| duration | 5 to 15 | 5 | The duration of the video in seconds. |
| resolution | 480P, 768P, 2K, 4K | 2K | The resolution of the generated video. 480P and 768P are native generation modes; 2K and 4K upscale a 768P base result. |
| seed |  | — | Random seed. A random seed is selected when omitted. |
| prompt_expansion_mode |  | balanced | How much effort to spend rewriting the prompt before generation. 'disabled' skips prompt expansion. 'fast' returns in about a second. 'balanced' picks per request. 'quality' spends up to ~30s on a richer prompt. |
| target_audio_url |  | — | Optional URL of an audio clip at least 2 seconds long (maximum 15 MB) to pin to the generated soundtrack. Longer clips are trimmed to the generated video's length, keeping the beginning. The original audio replaces the output soundtrack, padded with silence if shorter than the video, without changing playback speed. Exceptionally high sample rates may be resampled to 96 kHz. Accepts an HTTP(S) URL or a base64 data URI. |
| image_url |  | — | Optional URL of the image to use as the first frame. When provided, the output canvas follows this image. If only end_image_url is provided, the canvas follows that last frame instead. If both images are omitted, the request is handled as text-to-video (16:9 by default). |

## What can you do with MiniMax H3 Image to Video LoRA in opencode?

Turn a project's creative brief into short audiovisual assets for a website, game, or demo. Have the agent translate the brief into concrete compositions, actions, and sounds, then review fine details before adding the clips to the project.

### Short product promos

Build a brief product scene around one visible action, such as pouring a drink or opening a case, with matching sound. Choose text-led creation or supply product imagery where supported.

### Atmospheric footage

Create a short rainy street, windblown landscape, or quiet workshop shot. Specify the visible movement and environmental sounds as one scene.

### Animated explainer scenes

Illustrate one simple idea per clip, such as water filling a reservoir or a parcel moving along a conveyor. Use a concrete action that fits within 15 seconds.

### Storyboard motion tests

Test a short story beat before committing to a longer edit. Describe the opening composition, what changes, and the sound accompanying the action.

### Still artwork brought into motion

Use supplied artwork to guide a short animated scene. Describe how its subject moves and which visual features should remain consistent.

### Transitions between designed frames

Connect a prepared opening image to a prepared ending image. Describe the intermediate motion that carries the scene from one composition to the other.

### Character and style experiments

Apply a trained LoRA to explore a recurring character or visual treatment across short scenes. Review the results for consistency before assembling a sequence.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All opencode guides](https://spiral.ai/integrations/opencode)

## MiniMax H3 Image to Video LoRA in other agents

- [Amp](https://spiral.ai/integrations/amp/minimax-h3-image-to-video-lora)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/minimax-h3-image-to-video-lora)
- [Claude](https://spiral.ai/integrations/claude-desktop/minimax-h3-image-to-video-lora)
- [Claude Code](https://spiral.ai/integrations/claude-code/minimax-h3-image-to-video-lora)
- [Cline](https://spiral.ai/integrations/cline/minimax-h3-image-to-video-lora)
- [Codex](https://spiral.ai/integrations/codex/minimax-h3-image-to-video-lora)
- [Cursor](https://spiral.ai/integrations/cursor/minimax-h3-image-to-video-lora)
- [Devin](https://spiral.ai/integrations/devin/minimax-h3-image-to-video-lora)
- [dots](https://spiral.ai/integrations/dots/minimax-h3-image-to-video-lora)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/minimax-h3-image-to-video-lora)
- [Gemini](https://spiral.ai/integrations/gemini/minimax-h3-image-to-video-lora)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/minimax-h3-image-to-video-lora)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/minimax-h3-image-to-video-lora)
- [goose](https://spiral.ai/integrations/goose/minimax-h3-image-to-video-lora)
- [Grok](https://spiral.ai/integrations/grok/minimax-h3-image-to-video-lora)
- [Grok Build](https://spiral.ai/integrations/grok-build/minimax-h3-image-to-video-lora)
- [Hermes](https://spiral.ai/integrations/hermes/minimax-h3-image-to-video-lora)
- [Instinct](https://spiral.ai/integrations/instinct/minimax-h3-image-to-video-lora)
- [Manus](https://spiral.ai/integrations/manus/minimax-h3-image-to-video-lora)
- [Muse](https://spiral.ai/integrations/muse/minimax-h3-image-to-video-lora)
- [Muse Code](https://spiral.ai/integrations/muse-code/minimax-h3-image-to-video-lora)
- [n8n](https://spiral.ai/integrations/n8n/minimax-h3-image-to-video-lora)
- [Notion](https://spiral.ai/integrations/notion/minimax-h3-image-to-video-lora)
- [OpenClaw](https://spiral.ai/integrations/openclaw/minimax-h3-image-to-video-lora)
- [Perplexity](https://spiral.ai/integrations/perplexity/minimax-h3-image-to-video-lora)
- [Raycast](https://spiral.ai/integrations/raycast/minimax-h3-image-to-video-lora)
- [VS Code](https://spiral.ai/integrations/vscode/minimax-h3-image-to-video-lora)
- [Windsurf](https://spiral.ai/integrations/windsurf/minimax-h3-image-to-video-lora)
- [Zapier](https://spiral.ai/integrations/zapier/minimax-h3-image-to-video-lora)

## More opencode guides

- [MiniMax H3 Image to Video](https://spiral.ai/integrations/opencode/minimax-h3-image-to-video)
- [MiniMax H3 Max Recast](https://spiral.ai/integrations/opencode/minimax-h3-max-recast)
- [Marey Realism V1.5 Text to Video](https://spiral.ai/integrations/opencode/marey-realism-v1-5-text-to-video)
- [MiniMax H3 Reference to Video](https://spiral.ai/integrations/opencode/minimax-h3-reference-to-video)
- [Marey Realism 1.5 Pose Transfer](https://spiral.ai/integrations/opencode/marey-realism-1-5-pose-transfer)
- [MiniMax H3 Reference to Video LoRA](https://spiral.ai/integrations/opencode/minimax-h3-reference-to-video-lora)

## Questions about MiniMax H3 Image to Video LoRA in opencode

**Can opencode use MiniMax H3 Image to Video LoRA?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run MiniMax H3 Image to Video LoRA like any built-in tool.

**How much does MiniMax H3 Image to Video LoRA cost in opencode?**

`resolution`: 480P $0.08125, 768P $0.0975, 2K (default) $0.21125, 4K $0.26 per second. Billed on `duration`, default 5. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

**Do I need a fal account to use MiniMax H3 Image to Video LoRA in opencode?**

No. Spiral runs MiniMax H3 Image to Video LoRA on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up MiniMax H3 Image to Video LoRA in opencode?**

About two minutes: add the server, then sign in, then check it.

**Does opencode wait while MiniMax H3 Image to Video LoRA runs?**

MiniMax H3 Image to Video LoRA runs in the background. opencode starts the run, checks on it and gives you the video when it's ready.

**What is MiniMax H3 useful for?**

Use MiniMax H3 for short scenes where picture and sound need to work together, such as product promos, atmospheric footage, and animated story beats. Describe the visible action and audible events together.

**Does MiniMax H3 generate sound?**

Yes. MiniMax H3 generates synchronized stereo audio with its video, so include the sounds the scene needs in your brief.

**Which spoken languages does MiniMax H3 support?**

MiniMax documents stable dialogue support for Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish. Write the surrounding description in English and keep dialogue in its intended language.

**Can MiniMax H3 make a one-minute video?**

A single generation lasts at most 15 seconds. Plan a minute-long piece as several short shots and assemble them afterward.

**How should I write a MiniMax H3 prompt?**

Specify the visual style, opening composition, subject, action, and sounds. Use observable details such as a hand placing a cup on a counter instead of abstract instructions such as making the scene feel meaningful.

