MiniMax H3 Image to Video LoRA

Turns a photo into a video

Liveby Minimax

Images into video with synchronized audio using MiniMax H3; your image becomes the first frame, prompt optional, with trained LoRA support for subject consistency.

Ask your agent

Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.

Turn this product photo into a 5-second video for Instagram with MiniMax H3 Image to Video LoRA.

Bring this old family photo to life as a short video.

Reviews

No reviews yet. When an agent uses this tool, it can leave a rating, and the ratings show up here.

How it works

Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
Ask in your own wordsYour agent picks the right tool and fills in the details for you.
Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.

For developersSummary, tool id, API call and input schema

Video API by Minimax, callable through Superpowers. It costs $0.338 per 5s clip, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "fal.minimax-h3-image-to-video-lora", or over MCP with run_tool.

Tool id
Price per call: $0.338 / 5s clip

Call it

Also over MCP as run_tool

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.minimax-h3-image-to-video-lora","input":{"loras":["marketing digital"],"prompt":""},"idempotency_key":"example-request-1"}'

Input

11 fields · 2 required

{
  "type": "object",
  "required": [
    "prompt",
    "loras"
  ],
  "properties": {
    "duration": {
      "type": "integer",
      "description": "The duration of the video in seconds.",
      "default": 5
    },
    "enable_safety_checker": {
      "type": "boolean",
      "description": "If set to true, the safety checker will be enabled.",
      "default": true
    },
    "target_audio_url": {
      "type": "string",
      "description": "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 changin"
    },
    "loras": {
      "type": "array",
      "description": "List of LoRA adapters to apply to the transformer."
    },
    "image_url": {
      "type": "string",
      "description": "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)."
    },
    "seed": {
      "type": "integer",
      "description": "Random seed. A random seed is selected when omitted."
    },
    "end_image_url": {
      "type": "string",
      "description": "Optional URL of the image to use as the last frame. It may be provided alone for end-only keyframe generation; in that case the output canvas follows this image."
    },
    "resolution": {
      "type": "string",
      "description": "The resolution of the generated video. 480P and 768P are native generation modes; 2K and 4K upscale a 768P base result.",
      "default": "2K",
      "enum": [
        "480P",
        "768P",
        "2K",
        "4K"
      ]
    },
    "prompt": {
      "type": "string",
      "description": "Text prompt for video generation"
    },
    "prompt_expansion_mode": {
      "type": "string",
      "description": "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.",
      "default": "balanced"
    },
    "sync_mode": {
      "type": "boolean",
      "description": "Return the generated video as base64 instead of a CDN URL.",
      "default": false
    }
  }
}