MiniMax H3 LoRA API

Introduction

MiniMax H3 LoRA Reference to video builds one shot from your reference material and up to three of your own LoRA files on the open-weights MiniMax H3. Send up to nine images, three clips and three audio clips, refer to them by number in the prompt, and get back a 3 to 15 second MP4 with a stereo soundtrack at 480p, 540p, 768p or 1080p in one of seven aspect ratios.

Choose a mode by starting material

Key features

Three kinds of reference in one request

Images fix a face, an outfit or a room. Clips carry motion, pacing and camera movement, and their soundtracks come along automatically. Audio clips give a voice, a beat or a room tone to follow. Address them as Picture 1, Video 1 and Audio 1 so each input has one clear job.

LoRAs and references together

A character LoRA and reference stills of the same person hold identity better than either one alone. Add a style LoRA at a lower scale and the whole shot takes on your look without losing the subject.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

A recurring character in new scenes

Keep the same two or three stills of your character, add their LoRA, and change only the setting and action lines between shots. Each new scene starts from the same identity instead of re-rolling it.

Copy a move from a clip

Send a short clip of the dance, the fight beat or the camera move you want, plus a still of the new performer, and describe the new setting. Say outright that the person comes from the picture and only the motion from the clip: in our test, leaving that sentence out brought the dancer from the clip along with the move.

Put a voice under the picture

Add a voice or music clip as Audio 1 and tell the model who speaks or what the scene moves to. It is the quickest way to get a line of dialogue in a voice you already have.

Prompt guide & pro tips

Open with the map

Start the prompt with one short sentence per input: Picture 1 is the woman, Picture 2 is the hotel room, Video 1 is the dolly move. Then write the action and finish with the sound. Inputs without a job tend to get blended.

Watch the reference budget

The live estimate shows the full amount before you send.

Let the LoRA carry the look

When a style LoRA is loaded, do not also describe that style at length in the prompt. Describe the subject and the action, and let the weights handle the rendering.

API quick start

Call the MiniMax H3 LoRA API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model minimax/h3-lora/reference-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "minimax/h3-lora/reference-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "reference_image_urls": [
      "https://media.popnow.ai/influencer/examples/ava.webp"
    ],
    "aspect_ratio": "16:9",
    "resolution": "480p",
    "duration_seconds": 5
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

MiniMax H3 LoRA API questions

All MiniMax models

MiniMax H3 Singularity LoRA uses the same LoRAs on a fine-tune that keeps fast action and distant faces sharper, but renders more slowly and has no text to video.

• MiniMax H3 APIExpressive clips with audio, up to 2KFrom 28 credits for a 5-second clip
• MiniMax Speech 2.8 HD APIHigh-fidelity speech in 400+ voices with emotion controlFrom 18 credits per 1,000 characters
• MiniMax Music 3.0 APIFinished stereo songs, with vocals or instrumentalFrom 27 credits per run
• MiniMax H3 Singularity LoRA APICommunity-tuned H3 video that loads your own LoRAsFrom 45 credits for a 5-second clip
• MiniMax H3 Max APIFast clips with ambience, effects and musicFrom 38 credits for a 5-second clip
• MiniMax H3 LoRA APIMiniMax H3 video with sound and up to three of your LoRAsFrom 38 credits for a 5-second clip
• MiniMax H3 Image LoRA APIH3 stills and edits with up to three of your LoRAsFrom 7 credits per image
• MiniMax Speech 2.8 Turbo APIFast speech in 400+ voices with emotion controlFrom 11 credits per 1,000 characters

Other video APIs

• LTX-2.3 LoRA APILTX-2.3 clips with stereo sound and your own LoRAsFrom 18 credits for a 5-second clip
• LTX-2 19B LoRA APILTX-2 clips with sound and your own LoRA stylesFrom 14 credits for a 5-second clip
• Wan 2.2 LoRA APIWan 2.2 video with your LoRAs on either expert passFrom 18 credits for a 5-second clip
• Wan 2.2 5B LoRA APILight 720p Wan 2.2 clips that load your own LoRAsFrom 18 credits per run
• Wan 2.1 LoRA APIWan 2.1 video and edits with your own LoRAs, camera moves includedFrom 36 credits per run

More about MiniMax H3 LoRA

Try it

MiniMax H3 LoRA AI Video Generator onlineCreate videos with MiniMax H3 LoRA in PopNow

Docs

MiniMax H3 LoRA model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage to video guide for the PopNow APIWebhooks: get MiniMax H3 LoRA results without polling