MiniMax · Image model

MiniMax H3 Image

MiniMax's new image model: native 4K, up to 16 reference images in one result, and sharper text and detail.

The image version of MiniMax H3 (not the H3 video model), released November 10. Write a prompt, or edit and combine up to 16 reference images, up to 4K.

Released Nov 104K output16 reference imagesFrom 3 credits
Generate with MiniMax H3

Opens the generator with MiniMax H3 Image selected. Failed runs are refunded.

3D game art: knight duel

1 / 15

MiniMax H3 Image prompt ideas

Each image was made with MiniMax H3 from the prompt shown. Like one? Click "Use this prompt" and make your own.

Example

MiniMax H3 · 2K · 3:2

Prompt

A narrow cobbled street at blue hour just after rain, a cyclist in a yellow rain jacket riding in from the right, warm shop-window light reflected on the wet stones, low camera, 24mm lens, shallow depth of field

Use this prompt

What's new in MiniMax H3 Image

Native 4K

Generates 4096×4096 directly, no upscaling, with detail that holds up when you crop.

Fast, even at 4K

MiniMax says a 4K image takes under 10 seconds on its own API; here it usually takes 15 to 25 seconds, 4K included.

Up to 16 reference images

Give one image each for the person, outfit, product and setting, say "the person from Image 1, the coat from Image 2," and get one consistent scene.

Edit with one sentence

Recolor, add or remove objects, or swap the background. Say what changes and what stays, and the rest holds still.

Clear text in images

Headlines, menus and infographic labels come out as written when you put them in quotes.

Closer to real

MiniMax says details look natural, without the overly smooth look of many AI images.

Follows long prompts

MiniMax says it has the best prompt adherence among open-weight models, so a full brief or product spec can go in as written.

Pay per image, refunds on failure

No subscription: each image uses credits, and failed runs are refunded automatically.

Cards 2, 6 and 7 are based on MiniMax's launch post (November 2026); 4K and 16 references are this site's limits.

MiniMax H3 Image specs: what you can set here

OptionDetails
ModeText to image, image edit and multi-image composition
Resolution1K, 2K, 4K
Aspect ratioAuto (matches Image 1), 1:1, 4:5, 3:4, 2:3, 9:16, 1:3, 5:4, 4:3, 3:2, 16:9, 21:9, 3:1, or a custom width and height
Reference imagesUp to 16, called Image 1, Image 2… in order
Images per run1 to 10
FormatJPG, PNG or WebP
CompressionAdjustable for JPG and WebP, default 95
Prompt expansionOn by default, can be turned off; always on with references
Keep editingClick "Keep editing" on a result to use it as the reference
Credits per imageFrom 3, up to 25; multiplied by the number of images

MiniMax H3 Image examples: concept art, products, posters and multi-image edits

Images marked "Example" were made by us with MiniMax H3. Click any image to zoom in.

MiniMax H3 3D game art: knight duel

Chinese painting: blue-green landscape

MiniMax H3 Macro: red-eyed tree frog

Illustration: indigo-dyed rabbit

3D character: white-haired girl

Sci-fi: city at dusk

Food: crispy lace dumplings

Characters: otter and sheep sharing durian

Pixel art: white cat

Macro: jewel beetle

MiniMax H3 Surreal: giant cherries

Environment concept: ancient theater

Fantasy: dragon and rider on a red cliff

Tarot card: The Moon

Chinese text layout: logic puzzle

MiniMax H3 photoreal: a cyclist after rain

Vintage travel poster with clear text

MiniMax H3 concept art: a canyon city

Exploded watch with part labels

Perfume ad: glass, water and metal

New scene, same bottle and label

Two references, one scene

Café menu with every price right

Character sheet: front, side, back

4K furniture catalog shot

A first frame for video: coastal road

Small-text infographic: pour-over in 4 steps

What you can make with MiniMax H3 Image

Game art and concept art

Text to image

Lay out the scene, characters and depth in one go.

How to start: Say where the subject stands first, then the distance and the light.

Prompt

Concept art for a fantasy exploration game: a traveler in an ochre cloak on a cliff ledge in the lower left, a canyon city carved into sandstone in the distance with rope bridges and hanging gardens between towers, morning sun from the right, haze in the distance

Use this prompt

Combine several images

Image edit

Turn a person, an outfit and a product from separate images into one new scene.

How to start: Upload them in order and write "the person from Image 1, the product from Image 2."

Prompt

Put the person from Image 2 and the perfume bottle from Image 1 in one scene: the person sits by a seaside café window holding the bottle, keep the bottle's look and label unchanged, afternoon daylight

Use this prompt

Posters, menus and infographics

Text to image

Headlines, prices and step labels come out as you wrote them.

How to start: Put the exact words in quotes and say where they go and how big.

Prompt

Overhead shot of an open two-page café menu on white marble, header "HALF MOON CAFÉ", left page "MORNING": Oat latte 4.50, Cinnamon bun 3.80, Shakshuka 12.00; right page "AFTERNOON": Iced hojicha 5.00, Tomato toast 9.00

Use this prompt

Product shots and new scenes

Image edit

Keep the product's shape and label and change the background.

How to start: Upload the product shot and say what must not change and what the new background is.

Prompt

Keep the perfume bottle from Image 1 exactly the same, including its shape, label and text. Replace the background with a bathroom counter in soft morning side light, with a white towel nearby

Use this prompt

Exploded views and character sheets

Text to image

Lay out parts in an exploded view, or get a character's three views at once.

How to start: Say how the parts line up and what each label says.

Prompt

Isometric exploded view of a mechanical wristwatch, parts floating along a vertical axis from top to bottom: crystal, bezel, dial, hands, movement, case, strap, off-white background, thin black leader lines to small labels

Use this prompt

First frames for video

Text to image

Make a cinematic still first, then turn it into video.

How to start: Say where the camera is and which third of the frame the subject is in.

Prompt

A cinematic still to use as a video's first frame: a coastal road at dawn, a red vintage convertible in the right third of the frame, light mist over the sea, warm backlight

Want it to move? Try our Image to GIF tool.

Use this prompt

Make or edit an image with MiniMax H3 in three steps

1

Click "Generate with MiniMax H3"; the model is already selected. To edit, upload up to 16 reference images.

2

Describe what you want: subject, scene and light. For edits, say what changes and what stays. Pick the ratio, resolution and number of images.

3

Download the result, or click "Keep editing" to change it further.

MiniMax H3 Image prompt tips

  1. 1

    Start with the goal and who is doing what, then add style in visible terms like "soft side light" or "brushed metal," not just "premium."

  2. 2

    Lay out the frame first: how many subjects, where, from what angle and how much empty space. Then add details.

  3. 3

    Put on-image words in quotes with position, size and line breaks. For charts, give real numbers and units.

  4. 4

    Give each reference a job: "the product from Image 1, colors from Image 2, layout from Image 3."

  5. 5

    When editing, say what changes and what stays: "Make the cup on the left blue, keeping its shape, material and position."

  6. 6

    For grids, write "2 rows and 3 columns" rather than "2x3," which can flip.

MiniMax H3 Image or another model?

FeatureMiniMax H3 ImageSeedream 5.5GPT Image 2.6Nano Banana 2.1
Max resolution4K2K4K4K
ReferencesUp to 16Up to 10Up to 4Up to 1
Per run1–10111–4
Transparent backgroundNoYesNoNo
Best at4K, multi-image edits, concept artMulti-round edits, transparencyIn-image text, GIFs, SVGsCheap and quick
CreditsFrom 3From 3From 5From 2

All of these are in the same generator. MiniMax says H3 Image costs 50–70% of comparable mainstream models; run one prompt on each and compare.

Want cheap quick tries, or xAI's Grok? See the Grok image generator.

MiniMax H3 Image pricing

Pay per image with credits, no subscription: from 3 at 1K, 4 at 2K and 9 at 4K, a little more with extra references, multiplied by the number of images. The button shows the exact amount before you generate. Packs start at ¥9.9 and never expire; failed runs are refunded automatically.

Using MiniMax's API means your own account, key and token billing. Here you open the page and pay per image.

See credit packs

FAQ

Who made MiniMax H3 Image, and when was it released?

MiniMax released it on November 10, 2026, as the image version of H3. This site uses it through a third-party API and isn't affiliated with MiniMax.

Can MiniMax H3 make images, not just video?

Yes. H3 started as a video model; MiniMax H3 Image, released November 10, makes and edits still images. This page is about the image version.

Is this the same as the Hailuo AI image generator?

MiniMax says H3 Image is also on Hailuo AI. Here you use it in the browser with no app, paying per image.

How does MiniMax H3 Image edit work?

Write a prompt alone for text to image, or upload 1 to 16 reference images to edit and combine them. Refer to them as Image 1, Image 2 in your prompt.

What's the largest size?

1K, 2K or 4K; 4K is 4096×4096. Aspect ratios run from 1:3 to 3:1.

Is MiniMax H3 Image free to use?

Your first one can be free: new accounts get 4 credits, enough for one 1K image.

How many credits per image?

From 3 at 1K, 4 at 2K and 9 at 4K, a little more with references, times the number of images. The button shows the exact amount.

Do I need an API key? Is there a MiniMax H3 Image API?

No key needed here; just sign in and generate. If you want the API itself, MiniMax offers it on its developer platform.

Is MiniMax H3 Image open source? Can I run it locally?

MiniMax released the weights on Hugging Face. They're large and need a powerful GPU; if you'd rather not set that up, use it here in the browser.

Is there a Highspeed version?

MiniMax also offers a faster Highspeed version. This site uses the standard version, which MiniMax says is 1.5–2× as fast as mainstream models.

What if a run fails?

Your credits are refunded automatically.

Can I use the images commercially?

Yes. Under the terms of MiniMax and our API provider, the images you generate are yours and can be used commercially. Make sure you have the rights to the prompts and reference images you use, you're responsible for content involving other people's likeness or trademarks, and follow the laws where you live.

Turn ideas into images with the MiniMax H3 Image generator

Start with a sentence, or combine a few reference images. Need it big? Pick 4K.

From 3 credits per image. Failed runs are refunded.

Some example images belong to their owners. Contact us to have one removed.