by MiniMax

Open-weights H3 images with up to three LoRAs, including ones trained for H3 video

minimax/h3-image-open-lora/text-to-image
  • Up to 4K
  • Up to 9 reference images
  • 15 aspect ratios
  • Loads your own LoRA
  • Create Image
  • Edit Image

About MiniMax H3-Image Open Weights LoRA

Open-weights H3 images with up to three LoRAs, including ones trained for H3 video.

Call it with the model name minimax/h3-image-open-lora/text-to-image on POST /jobs/createTask, from $0.042.

Introduction

This generator accepts H3-Image scene descriptions with up to three LoRA attachments to influence the resulting still.

Key features

In our tests a VHS H3 video-model LoRA applied to still generation. A fixed seed allowed an on/off comparison that showed changes in texture and composition.

Request parameters

ParameterRequiredDescription
aspect_ratioNoThe shape of the frame: wide, square or tall. 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 2:1 · 1:2 · 3:1 · 1:3 · 5:4 · 4:5 · Default: 1:1
lorasNoAdd LoRA weights compatible with this model to guide its style or character. Default: []
output_formatNoFile type of the result. jpeg · png · webp · Default: jpeg
promptYesDescribe what you want to make.
resolutionNoChoose an available output size. 1k · 1.5k · 2k · 3k · 4k · Default: 1k
seedNoUse the same seed and settings for more controlled comparisons. ≥ 0 · ≤ 2147483647

Pricing

Prices are in USD and charged to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

OptionUSD per image
resolution 1K$0.042
resolution 1.5K$0.054
resolution 2K$0.066
resolution 3K$0.114
resolution 4K$0.162

Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.

Use cases

Use the tested tape treatment for a diner dance or a neon-lit racing arcade, then inspect the frame for text carried by the LoRA.

Prompt guide & pro tips

Start prompt with the trigger word and provide a reachable direct weight link. Fix the seed for comparison, check the effect with attachments removed, and review any watermark lettering.

API quick start

Call the MiniMax H3-Image Open Weights 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-. API calls are billed in USD from your PopNow balance.
  2. Send the request. POST /jobs/createTask with model minimax/h3-image-open-lora/text-to-image 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-image-open-lora/text-to-image",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "output_format": "jpeg"
  }
}'

# 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-Image Open Weights LoRA API questions

How much does the MiniMax H3-Image Open Weights LoRA API cost?

MiniMax H3-Image Open Weights LoRA starts at $0.042 per image with Create Image, its lowest-priced task. Prices by option: 1K $0.042 per image, 1.5K $0.054 per image, 2K $0.066 per image, 3K $0.114 per image. API usage is charged in USD to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.

What is the model name for MiniMax H3-Image Open Weights LoRA in the API?

Put minimax/h3-image-open-lora/text-to-image for Create Image; minimax/h3-image-open-lora/edit for Edit Image in the model field of POST /jobs/createTask.

Can H3 video-model LoRAs alter H3-Image stills?

They did in our tests: a VHS LoRA changed texture and composition, and a 1930s cartoon LoRA restyled an existing image while preserving its pose.

Where did the text in the diner corner come from?

The VHS sample included the word vh5tape in its lower-left corner. Some LoRAs reproduce text or watermarks from their training sets as part of the visual treatment.

What is a useful check that my weight file applied?

Place its trigger at the beginning, hold seed and other settings fixed, and compare one run with the LoRA against one without it. Look for both a style change and a possible composition change.

Does attaching three files triple the LoRA surcharge?

No: the per-image LoRA increment is fixed whether zero, one or three files are attached. Output size still sets the tier, and editing inputs after the first add their own fees; failed tasks are free.

Which H3 option should I use without weight attachments?

[Open Weights](/models/minimax-h3-image-open) provides five tiers and seed control without the LoRA version's fixed increment. [MiniMax H3-Image](/models/minimax-h3-image) offers MiniMax hosting and sixteen editing references. The older [H3 Image LoRA](/models/minimax-h3-image-lora) makes single frames with the video model rather than this image checkpoint.

What are the limits of the MiniMax H3-Image Open Weights LoRA API?

Resolutions: 1K · 1.5K · 2K · 3K · 4K; Aspect ratios: 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 +9; Prompt length (characters): 5,000. Requests outside these limits are rejected before anything is charged.

Can I try MiniMax H3-Image Open Weights LoRA without writing code?

Run MiniMax H3-Image Open Weights LoRA in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.

All MiniMax models

More about MiniMax H3-Image Open Weights LoRA