Minimax H3 Text To Video LoRA API Documentation

Minimax H3 Text To Video LoRA API Documentation

Playground

MiniMax H3 Open Weights Text to Video with custom LoRA support generates coherent videos from text prompts, with 480P / 540P / 768P output, 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 Text-to-Video LoRA Open Weights runs the open-weights edition of MiniMax H3 with LoRA support on WaveSpeedAI. This endpoint is separate from the official minimax/h3 API and uses its own 480p / 768p / 1080p resolution options and per-second pricing.

MiniMax H3 generates video and native stereo audio in a single pass. Describe both the visuals and the sound in one prompt, and the model produces an MP4 with synchronized dialogue, sound effects, music, or ambience.

Why Choose This?

• Open-weights MiniMax H3 workflow
  Use the open-weights edition of MiniMax H3 through WaveSpeedAI-hosted infrastructure.

• Native stereo audio
  Generate visuals and synchronized stereo audio together in one pass.

• LoRA support
  Load up to 3 LoRA weights per request, each with its own scale.

• Text-to-video generation
  Generate complete videos directly from text prompts.

• Prompt-controlled soundtrack
  Use an Audio: line in the prompt to guide music, dialogue, ambience, and sound effects.

• Flexible aspect ratios
  Supports landscape, vertical, square, classic, and cinematic aspect ratios.

Parameters

How to Use

1. Write the prompt — Describe the visual scene, timeline, camera movement, and audio direction.
2. Choose aspect ratio — Select the format that matches your target platform or composition.
3. Choose resolution — Use 480p for lower-cost generation, 540p for a mid-price step up, 768p for higher-resolution output, or 1080p for full-HD output.
4. Set duration — Choose a duration from 3 to 15 seconds.
5. Add LoRAs optional — Provide up to 3 LoRA files with individual scale values.
6. Set seed optional — Use a fixed seed when reproducibility is needed.
7. Submit — Generate the final MP4 with native stereo audio.

Pricing

Pricing is based on generated video duration and selected resolution.

Duration is capped at 15 seconds for pricing. LoRA loading does not add a separate charge.

Best Use Cases

• LoRA-guided video generation — Apply custom visual styles, subjects, or concepts with LoRA weights.
• Text-to-video creation — Generate complete videos directly from natural-language prompts.
• Music and audio-driven scenes — Create videos with native stereo sound, ambience, dialogue, or music.
• Character and style testing — Use LoRAs to guide consistent looks across prompt variations.
• Creative prototyping — Test visual timing, camera movement, and soundtrack direction quickly.
• Social video content — Generate short clips for landscape, vertical, square, or cinematic formats.

Pro Tips

• Write prompts as a timeline with clear timestamped beats.
• Include an Audio: line to guide soundtrack, ambience, voice, and effects.
• Use action verbs instead of only describing mood or visual style.
• Keep the first test short, then increase duration once the scene direction works.
• Use a fixed seed when comparing LoRA scale or prompt variations.
• Start LoRA scale around 0.8–1.0, then adjust based on how strongly the LoRA affects the result.
• Use a short negative list such as no subtitles, no extra text, or no extra people when needed.

Related Models

• MiniMax H3 Text-to-Video Open Weights — Generate video with native stereo audio directly from a text prompt.
• MiniMax H3 Image-to-Video Open Weights — Animate a first-frame image with prompt-guided motion and audio.
• MiniMax H3 Reference-to-Video Open Weights — Generate video from image, video, or audio references with prompt guidance.

Reference

• How to train your LoRA?
• How to use your LoRA?

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",
  "aspect_ratio": "16:9",
  "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/text-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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${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