logo
RunComfy
  • ComfyUI
  • TrainerNew
  • Models
  • API
  • Pricing
discord logo
MODELS
Explore
All Models
LIBRARY
Generations
MODEL APIS
API Docs
API Keys
ACCOUNT
Usage

Minimax H3 Reference to Video: 2K Reference-Guided Video Generation on Models and API | RunComfy

minimax/minimax-h3/reference-to-video

Minimax H3 Reference to Video turns reference images, clips, and audio plus a prompt into a 2K video of 5 to 15 seconds, holding subject and motion consistent.

Table of contents

1. Get started2. Authentication3. API referenceSubmit a requestMonitor request statusRetrieve request resultsCancel a request4. File inputsHosted file (URL)5. SchemaInput schemaOutput schema

1. Get started

Use RunComfy's API to run minimax/minimax-h3/reference-to-video. For accepted inputs and outputs, see the model's schema.

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/minimax/minimax-h3/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "The woman from the reference steps out of the shadowed doorway into the low sun, dust lifting around her boots as she scans the street ahead. The camera tracks with her at shoulder height, warm light rakes across her face, and the background falls away into haze. Cinematic pacing, natural movement, anamorphic look.",
    "reference_images": [
      "https://playgrounds-storage-public.runcomfy.net/tools/7394/media-files/ref-promo.webp"
    ],
    "aspect_ratio": "16:9",
    "duration": 5,
    "resolution": "2k"
  }'

2. Authentication

Set the YOUR_API_TOKEN environment variable with your API key (manage keys in your Profile) and include it on every request as a Bearer token via the Authorization header: Authorization: Bearer $YOUR_API_TOKEN.

3. API reference

Submit a request

Submit an asynchronous generation job and immediately receive a request_id plus URLs to check status, fetch results, and cancel.

curl --request POST \
  --url https://model-api.runcomfy.net/v1/models/minimax/minimax-h3/reference-to-video \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer <token>" \
  --data '{
    "prompt": "The woman from the reference steps out of the shadowed doorway into the low sun, dust lifting around her boots as she scans the street ahead. The camera tracks with her at shoulder height, warm light rakes across her face, and the background falls away into haze. Cinematic pacing, natural movement, anamorphic look.",
    "reference_images": [
      "https://playgrounds-storage-public.runcomfy.net/tools/7394/media-files/ref-promo.webp"
    ],
    "aspect_ratio": "16:9",
    "duration": 5,
    "resolution": "2k"
  }'

Monitor request status

Fetch the current state for a request_id ("in_queue", "in_progress", "completed", or "cancelled").

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
  --header "Authorization: Bearer <token>"

Retrieve request results

Retrieve the final outputs and metadata for the given request_id; if the job is not complete, the response returns the current state so you can continue polling.

curl --request GET \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
  --header "Authorization: Bearer <token>"

Cancel a request

Cancel a queued job by request_id; in-progress jobs cannot be cancelled.

curl --request POST \
  --url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
  --header "Authorization: Bearer <token>"

4. File inputs

Hosted file (URL)

Provide a publicly reachable HTTPS URL. Ensure the host allows server-side fetches (no login/cookies required) and isn't rate-limited or blocking bots. Recommended limits: images ≤ 50 MB (~4K), videos ≤ 100 MB (~2–5 min @ 720p). Prefer stable or pre-signed URLs for private assets.

5. Schema

Input schema

{
  "type": "object",
  "title": "Input schema",
  "required": [
    "prompt",
    "reference_images",
    "aspect_ratio",
    "duration",
    "resolution"
  ],
  "properties": {
    "prompt": {
      "title": "Prompt",
      "description": "Description of the scene, interaction, motion and visual style. 1-4000 characters.",
      "type": "string",
      "default": "The woman from the reference steps out of the shadowed doorway into the low sun, dust lifting around her boots as she scans the street ahead. The camera tracks with her at shoulder height, warm light rakes across her face, and the background falls away into haze. Cinematic pacing, natural movement, anamorphic look."
    },
    "reference_images": {
      "title": "Reference Images",
      "description": "Reference images guiding subject, product, style or composition. Up to 9. At least one reference image or video is required.",
      "type": "array",
      "default": [
        "https://playgrounds-storage-public.runcomfy.net/tools/7394/media-files/ref-promo.webp"
      ],
      "items": {
        "type": "string",
        "format": "image_uri"
      },
      "maxItems": 9
    },
    "reference_videos": {
      "title": "Reference Videos",
      "description": "Reference videos guiding movement, pacing or interaction. Up to 3. At least one reference image or video is required.",
      "type": "array",
      "items": {
        "type": "string",
        "format": "video_uri"
      },
      "maxItems": 3
    },
    "reference_audios": {
      "title": "Reference Audios",
      "description": "Optional reference audio. Up to 3. Cannot be provided without an image or video reference.",
      "type": "array",
      "items": {
        "type": "string",
        "format": "audio_uri"
      },
      "maxItems": 3
    },
    "aspect_ratio": {
      "title": "Aspect Ratio",
      "description": "Output aspect ratio.",
      "type": "string",
      "enum": [
        "21:9",
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16"
      ],
      "default": "16:9"
    },
    "duration": {
      "title": "Duration",
      "description": "Length of the generated video in seconds.",
      "type": "integer",
      "minimum": 5,
      "maximum": 15,
      "default": 5
    },
    "resolution": {
      "title": "Resolution",
      "description": "Output video resolution.",
      "type": "string",
      "enum": [
        "2k"
      ],
      "default": "2k"
    }
  }
}

Output schema

{
  "output": {
    "type": "object",
    "properties": {
      "image": {
        "type": "string",
        "format": "uri",
        "description": "single image URL"
      },
      "video": {
        "type": "string",
        "format": "uri",
        "description": "single video URL"
      },
      "images": {
        "type": "array",
        "description": "multiple image URLs",
        "items": {
          "type": "string",
          "format": "uri"
        }
      },
      "videos": {
        "type": "array",
        "description": "multiple video URLs",
        "items": {
          "type": "string",
          "format": "uri"
        }
      }
    }
  }
}
Follow us
  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
Support
  • Discord
  • Email
  • System Status
  • Affiliate
Video Models
  • Wan 2.6 Flash
  • Wan 2.6 Text to Video
  • Hailuo 2.3 Fast Standard
  • Happy Horse 1.1 reference to video
  • Seedance 2.5 Reference to Video
  • Seedance 2.0 Pro
  • View All Models →
Image Models
  • Seedream 5.0 Pro Image Edit
  • seedream 4.0
  • Flux 2 Flash Edit
  • Nano Banana Pro
  • Nano Banana 2 Edit
  • GPT Image 2 Image Edit
  • View All Models →
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.