Minimax H3 Image To Video LoRA API Documentation

Minimax H3 Image To Video LoRA API Documentation

Playground

Try it on WaveSpeedAI!

MiniMax H3 Open Weights Image to Video animates a first-frame image, optionally with last-frame guidance, into coherent 480P / 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

Run the open-weights edition of MiniMax H3 on WaveSpeedAI’s own GPU infrastructure. This endpoint is separate from the official minimax/h3 API: same model family, independently hosted, with its own 480p/768p resolutions and per-second pricing.

MiniMax H3 is an omni-modal video model that generates picture and native stereo audio in a single pass — dialogue, sound effects, and music are produced together during generation, never added as a separate dubbing step. Give it a first-frame image plus a prompt and it animates the scene with a matching soundtrack.


How to Write a Great Prompt

The image sets the look; the prompt directs the motion and the sound over time. Write it as a timeline, not a one-line description:

  1. Motion timeline — timestamped beats: “[0s-2s] she breathes and blinks … [2s-5s] a warm smile as the camera pushes in …”. Beats keep the animation moving instead of drifting.
  2. Camera — state it explicitly, including when it should hold: “slow push-in, then lock off, no cuts”.
  3. Audio — put every sound in an Audio: line with entrance cues: “Audio: quiet room tone, a soft piano melody that swells at 3s.” Omit this and the model picks a soundtrack for you.
  4. On-screen text — spell out any readable words in quotes and add “do not add other text, no subtitles.”

First / last frame (optional) — supply last_image to lock the ending; the model generates the motion between the first and last frames. Great for a controlled emotional arc.

Tips

  • Use clear, well-lit images; the output canvas follows the input image’s aspect ratio.
  • Verbs beat adjectives — write the action, not just the mood.
  • Iterate at 5s, then deliver at your final length; a short negative list (“no extra people, no cuts”) is free.

Parameters

ParameterRequiredDescription
promptYesDesired motion, camera movement, and an Audio: line for the soundtrack.
imageYesFirst-frame image URL. The output canvas follows this image’s aspect ratio.
last_imageNoOptional last-frame image URL. When set, the video interpolates from the first frame to this frame.
resolutionNo480p (faster, lower cost) or 768p (native canvas). Default: 480p.
durationNoOutput length in seconds, 315. Default: 5.
seedNoFixed seed for reproducible output.
lorasNoUp to 3 LoRA weights, each {path, scale}; path is a LoRA file URL.

Specifications

ItemDetail
OutputMP4 with native stereo audio
Frame rate24 fps
Resolution480p or 768p
Duration315 seconds (snaps to the model’s frame grid, so a 5s request lands at ~5.2s)
InputFirst-frame image (optional last frame for interpolation)
SeedSupported

Pricing

Billed per generated second:

ResolutionPrice per second5s15s
480p$0.05$0.25$0.75
768p$0.10$0.50$1.50

Explore the MiniMax H3 Open Weights Family

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,
  "seed": -1
}
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/image-to-video-lora" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 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) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Text description of the desired motion, scene, and soundtrack. Audio is generated natively together with the video.
imagestringYes-First-frame image URL. The output canvas follows this image's aspect ratio.
last_imagestringNo--Optional last-frame image URL. When provided, the video interpolates from the first frame to this frame.
resolutionstringNo480p480p, 768pOutput video resolution. 768p is the model's native canvas; 480p is a faster, lower-cost tier.
durationintegerNo53, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Output video duration in seconds.
seedintegerNo-1-The random seed to use for the generation. -1 means a random seed will be used.
lorasarray<object>No0 ~ 3 itemsList of LoRAs to apply (max 3).

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.