wowmachine
smart_toy

MiniMax H3 Image Edit

minimax/h3-image-edit

MiniMax H3 Image Edit is the image-editing mode of MiniMax H3 — also known as Hailuo 3.0 — the open-weights multimodal model MiniMax launched in July 2026. Feed it up to nine reference images and a written instruction and it re-renders the subject into a new scene, outfit or style while holding on to their identity, at 1K or 2K.

Input

Describe the new scene, outfit or style. Refer to your references in order as <Picture 1>, <Picture 2> and so on.

Reference images (1-9). The subject's identity is taken from these; the first one also sets the default aspect ratio.

add

0 / 9

Output aspect ratio. Leave empty to match the first reference image.

Output resolution: 1k (about 1 megapixel) or 2k (about 4 megapixels).

Output file format.

Seed for reproducible results. Leave empty for a random seed.

min: 0max: 2147483647

Output

image

Run the model to see output here.

Pricing

**Priced per edited image by resolution and number of references.** | References | 1k | 2k | |---|---|---| | 1 image | 3 | 9 | | 3 images | 4 | 10 | | 5 images | 5 | 11 | | 9 images | 8 | 13 | *Cred...

Features

## What MiniMax H3 Image Edit is good at MiniMax H3 — widely called Hailuo 3.0 — is the model MiniMax launched on 31 July 2026 as an open-weights, general-purpose multimodal generator. Instead of tra...

API Examples

curl -X POST \
  /api/v1/model/minimax/h3-image-edit \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {}
}'

Tags