Get API key

by MiniMax

Community-tuned H3 video that loads your own LoRAs

minimax/h3-singularity-lora/image-to-videoFrom 45 creditsfor a 5-second clip · $0.45Reference to Video
  • Up to 1080p
  • 3–15s clips
  • Start and end frames
  • Up to 9 reference images
  • 7 aspect ratios
  • Loads your own LoRA
  • Image to Video
  • Reference to Video
  • Extend Video
See examples

About MiniMax H3 Singularity LoRA

MiniMax H3 Singularity LoRA runs Singularity, a community fine-tune of the open-weights MiniMax H3 trained for crisper fast motion, cleaner distant faces and less plastic-looking skin, with up to three of your own H3 LoRAs loaded per request.

Call it with the model name minimax/h3-singularity-lora/image-to-video on POST /jobs/createTask, from 47 credits for a 5-second clip ($0.47). New accounts get 30 free credits to try it in the Playground first.

Introduction

MiniMax H3 Singularity LoRA Image to video animates your opening frame on Singularity, a community fine-tune of the open-weights MiniMax H3 trained for crisp fast motion, and lets you load up to three of your own H3 LoRAs. Clips run 3 to 15 seconds at 480p, 540p, 768p or 1080p with a stereo soundtrack, keep the shape of your frame, and can end on an optional closing frame.

Choose a mode by starting material

What you haveMode
an opening imageMiniMax H3 Singularity LoRA Image to video
reference images, clips or audioMiniMax H3 Singularity LoRA Reference to video
a written scene onlyMiniMax H3 LoRA Text to video

Key features

Tuned for movement

Singularity was trained further on high-dynamic-range footage to cut motion blur during fast action and to keep faces from collapsing in wider shots. Spins, strikes and whip pans are where the difference from a regular video model shows most.

Your H3 LoRAs load unchanged

The fine-tune keeps MiniMax H3's architecture, so the LoRAs you already use with H3 load here as they are, up to three per request with their own strengths from 0 to 4.

Request parameters

ParameterRequiredDescription
duration_secondsNoHow long the clip runs. You pay per second. ≥ 3 · ≤ 15 · Default: 5
image_urlYesThe picture to start from.
last_image_urlNoOptional final frame, so the clip ends exactly where you want.
lorasNoLoad your own LoRA files to lock in a style or character. Default: []
promptYesDescribe what happens after the opening frame: the action, the camera and the sound.
resolutionNoOutput size. Bigger sizes look sharper and cost more. 480p · 540p · 768p · 1080p · Default: 480p
seedNoReuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647

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.

OptionCredits per second≈ USD
resolution 480p9.38$0.094
resolution 540p14.06$0.14
resolution 768p18.75$0.19
resolution 1080p37.5$0.38

Each task is rounded up to whole credits, so one run at the lowest tier costs 47 credits for a 5-second clip ($0.47).

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

Use cases

A fight or stunt beat from one still

Start from a frame with the character already mid-action and write the next beat: the draw, the strike, the landing. Keep it to three to six seconds so the motion stays tight.

Performance clips from a promo photo

Turn a dancer's or performer's photo into a short routine with the camera orbiting them. The fine-tune holds the face while the body moves fast.

Stylised action with a LoRA

Add an anime or film-stock LoRA and the same action beat takes on that look, while Singularity keeps the movement readable.

Prompt guide & pro tips

Two or three beats, each with a camera move

Write: she spins, draws the blade, the camera whips around her. Physical verbs and one camera instruction per beat give the fine-tune something concrete to sharpen. Close with an Audio: line for impacts and breath.

Start from motion, not a pose

Opening frames where the subject is already moving give smoother results than a static standing pose. If you only have a posed frame, make the first beat a clear, simple movement.

Expect a slower render

A five-second 480p clip took about 80 seconds in our testing, around twice the regular MiniMax H3 LoRA family. Set timeouts accordingly and settle the action at 480p before paying for 1080p.

API quick start

Call the MiniMax H3 Singularity 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-singularity-lora/image-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-singularity-lora/image-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "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 Singularity LoRA API questions

How much does the MiniMax H3 Singularity LoRA API cost?

MiniMax H3 Singularity LoRA starts at 45 credits ($0.45) for a 5-second clip with Reference to Video, its cheapest task. Prices for Image to Video by option: 480p 9.38 credits per second, 540p 14.06 credits per second, 768p 18.75 credits per second, 1080p 37.5 credits per second. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.

What is the model name for MiniMax H3 Singularity LoRA in the API?

Put minimax/h3-singularity-lora/image-to-video for Image to Video; minimax/h3-singularity-lora/reference-to-video for Reference to Video; minimax/h3-singularity-lora/video-extend for Extend Video in the model field of POST /jobs/createTask.

Do my MiniMax H3 LoRAs work on it?

Yes. Singularity keeps the H3 architecture, so LoRAs trained for H3 load as they are. We ran the same LoRA file on both families.

Is it slower?

Yes. A five-second 480p clip took about 80 seconds in our testing, roughly twice the regular family.

Why is there no text-to-video?

This family offers the three Singularity modes that start from your material: an opening frame, references, or a clip to extend. For text-only prompts use MiniMax H3 LoRA Text to video.

What are the limits of the MiniMax H3 Singularity LoRA API?

Clip length: 3–15 s; Resolutions: 480p · 540p · 768p · 1080p; Prompt length (characters): 7,000. Requests outside these limits are rejected before anything is charged.

Can I try MiniMax H3 Singularity LoRA without writing code?

Yes. The Playground runs MiniMax H3 Singularity LoRA on your PopNow credits, needs no API key, and shows the matching code for every run.

All MiniMax models

The regular MiniMax H3 LoRA is quicker and cheaper for calm, slow shots and adds text-to-video. Switch to Singularity when a fight, a dance or a whip pan starts to smear.

More about MiniMax H3 Singularity LoRA