Minimax H3 Image Edit API Documentation
Playground
Try it on WaveSpeedAI!MiniMax H3 Open Weights Image Edit re-renders a subject from up to 9 reference images into a new scene, outfit or style from a text instruction, preserving identity at 1K or 2K resolution. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Features
Run the open-weights edition of MiniMax H3 as a reference-guided image editor on WaveSpeedAI’s own GPU infrastructure. Provide 1 to 9 reference images and an instruction; the model re-renders the subject into a new scene, outfit, pose or art style while preserving identity, at 1k or 2k resolution.
Why Choose This?
-
Strong identity preservation
Faces, hairstyles, accessories and clothing details carry over from the references. -
Scene, outfit and style changes
Move a person to a new location, change what they wear, or restyle the image as a painting or animation. -
Multi-image references
Combine up to 9 references, addressed in the prompt as<Picture 1>,<Picture 2>, and so on. -
Aspect ratio follows your input
By default the output keeps the aspect ratio of the first reference image; override it withaspect_ratio.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | The edit instruction. Refer to references as <Picture 1> .. <Picture N>. |
| images | Yes | 1 to 9 reference image URLs. |
| aspect_ratio | No | Output aspect ratio. Options: 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, or 21:9. Defaults to the first reference image’s aspect ratio. |
| resolution | No | Output resolution: 1k (default) or 2k. |
| output_format | No | jpeg (default), png or webp. |
| seed | No | Random seed. -1 picks a random seed. |
How to Use
- Upload references — One clear image of the subject is enough; add more for outfits, props or additional people.
- Describe the new image — State the new scene, outfit, pose and style explicitly, e.g.
The same woman from <Picture 1>, now wearing a red leather jacket, standing in a neon-lit Tokyo alley at night. Photorealistic still. - Choose resolution —
1kfor iteration,2kfor final assets. - Submit — Receive the edited image URL.
Pricing
Pricing is based on the selected resolution.
| Resolution | Cost per image |
|---|---|
| 1k | $0.03 |
| 2k | $0.09 |
Best Use Cases
- Virtual try-on and outfit swaps — Keep the person, change the clothes.
- Scene relocation — Put a subject into a new environment with matching light.
- Style transfer — Oil painting, anime or illustration versions of a photo.
- Character sheets — Consistent renders of one character across settings.
Pro Tips
- Describe the new scene fully instead of only naming the reference; short prompts that just say “the person from <Picture 1>” tend to reproduce the reference.
- For style transfer, say so explicitly, e.g.
This is a painting, not a photograph. - Keep the subject’s key features in the prompt (hair, glasses, beard) when they matter.
- Fix the
seedto iterate on wording without changing the composition.
Related Models
- MiniMax H3 Text-to-Image — Generate stills from text with the same model.
- MiniMax H3 Reference-to-Video — Animate reference images into video with native audio.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3/image-edit" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}")
RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The edit instruction. Refer to the reference images as <Picture 1>, <Picture 2>, ... in order. Describe the new scene, outfit or style you want; the subject's identity is taken from the references. | |
| images | array<string> | Yes | - | 1 ~ 9 items | Reference images to edit from (1 to 9 URLs). The first image also sets the output aspect ratio unless aspect_ratio is given. |
| aspect_ratio | string | No | - | 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9 | The aspect ratio of the generated image. Defaults to the aspect ratio of the first reference image. |
| resolution | string | No | 1k | 1k, 2k | Total output resolution tier: 1k (~1 megapixel) or 2k (~4 megapixels). |
| output_format | string | No | jpeg | jpeg, png, webp | The format of the output image. |
| seed | integer | No | - | - | The random seed to use for the generation. -1 means a random seed will be used. |
| enable_base64_output | boolean | No | false | - | If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN. |
| enable_sync_mode | boolean | No | false | - | If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |