Minimax H3 Singularity Image To Video API Documentation

Minimax H3 Singularity Image To Video API Documentation

Playground

MiniMax H3 Singularity Open Weights Image-to-Video animates a first-frame image, with optional last-frame guidance, into coherent 480P / 540P / 768P videos with native stereo audio, 5-15 second duration, flexible aspect ratios, and per-second billing. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax H3 Singularity Image-to-Video runs the open-weights edition of MiniMax H3 Singularity on WaveSpeedAI infrastructure. Provide a first-frame image and a text prompt to generate a video with prompt-guided motion, camera movement, scene progression, and native stereo audio.

Why Choose This?

• Open-weights video generation
  Run MiniMax H3 Singularity on WaveSpeedAI-hosted GPU infrastructure.

• Image-to-video generation
  Animate a first-frame image with prompt-guided subject motion and scene progression.

• Native stereo audio
  Generate video and synchronized stereo audio together in a single pass.

• Optional last-frame guidance
  Use last_image to guide the ending frame and create a more controlled start-to-end transition.

• Prompt-guided motion and sound
  Describe camera movement, action, timing, dialogue, music, ambience, and sound effects directly in the prompt.

• Four resolution tiers
  Generate at 480p, 540p, 768p, or 1080p.

• Flexible duration
  Generate videos from 3 to 15 seconds.

Parameters

How to Use

1. Upload the first-frame image — Provide the image that defines the opening frame, subject, composition, and visual direction.
2. Add last-frame guidance optional — Use last_image when you want stronger control over the final frame or ending direction.
3. Write the prompt — Describe subject motion, camera movement, timing, scene progression, and audio direction.
4. Choose resolution — Select 480p, 540p, 768p, or 1080p.
5. Set duration — Choose a video length from 3 to 15 seconds.
6. Set seed optional — Use a fixed seed when reproducibility is needed.
7. Submit — Generate the final video with native stereo audio.

Pricing

Pricing is based on generated video duration and selected resolution.

Best Use Cases

• Image animation — Turn portraits, illustrations, product images, or concept art into motion.
• Character animation — Add expressions, body movement, and camera motion to character images.
• Start-and-end-frame control — Use image and last_image to guide both the opening and ending of the video.
• Cinematic scenes — Combine character action, camera movement, atmosphere, and audio in one generation.
• Audio-driven scenes — Generate dialogue, music, ambience, and sound effects together with the video.
• Creative prototyping — Test motion direction, camera behavior, timing, and audio from a still image.

Pro Tips

• Use a clear, well-lit first-frame image for stronger subject and composition consistency.
• Use last_image when the final pose, framing, or scene state matters.
• Describe visible actions with specific verbs instead of relying only on mood or style descriptions.
• Break complex actions into clear timeline beats when timing matters.
• Specify camera movement explicitly, including when the camera should remain still.
• Include an Audio: line when you want stronger control over dialogue, music, ambience, or sound effects.
• Start with a 5s generation while testing motion direction before increasing duration.
• Use 480p for lower-cost iteration before moving to higher resolutions.
• Set a fixed seed when comparing prompt changes.

Notes

• prompt and image are required.
• last_image is optional.
• duration supports 3–15 seconds and defaults to 5.
• resolution supports 480p, 540p, 768p, and 1080p.
• resolution defaults to 480p.
• The output canvas follows the first-frame image’s aspect ratio.
• Video and native stereo audio are generated together.

Related Models

• MiniMax H3 Singularity Image-to-Video Open Weights — Animate a first-frame image with prompt-guided motion and native audio.
• MiniMax H3 Singularity Reference-to-Video Open Weights — Generate videos with image, video, and audio reference guidance.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "resolution": "480p",
  "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3-singularity/image-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters