MiniMax H3 Image, the open-weights release of MiniMax's image model, edits images from natural-language instructions with up to 9 input images and custom LoRA weights, native output from 1K to 4K. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
/filters:quality(85)/examples/9744313b0f9a696b369d1e8e2b7b6a4c/835c79cc-7a84-4f28-92b0-ba091bd052aa-e3acac9ef4fc.webp)
$0.03per run·~33 / $1
/filters:quality(82)/examples/9744313b0f9a696b369d1e8e2b7b6a4c/835c79cc-7a84-4f28-92b0-ba091bd052aa-e3acac9ef4fc.webp)
Change the environment to a sunlit Mediterranean hotel terrace overlooking the sea, with pale stone walls, soft blue water, and warm natural daylight. Change his outfit from the black leather jacket into an elegant cream linen blazer over a fitted black open-collar shirt, with subtle gold accessories. Keep the result realistic, masculine, stylish, and editorial, with sharp facial detail, natural skin texture, refined fabric detail, and premium luxury fashion photography. Preserve the man’s exact face, hairstyle, body pose, hand position, and framing.
/filters:quality(82)/examples/0139c97e6dfbaf9dec104fb9ba570030/95e167e2-e3db-4259-af3e-6922b64c82c6-2e2bc5c8be00.webp)
Change the season to winter: she wears a cream knitted sweater and a scarf, snow falling softly in a pine forest behind her.
/filters:quality(82)/examples/c392911df6b5b16a323373b1351483bc/d5ce7aff-5419-4584-8306-ee6ebd34eaee-ecbdffd96369.webp)
Dress him in a tailored navy suit and place him in a bright modern office with large windows. Keep his face unchanged.
MiniMax H3 Image Open-Weights Edit LoRA runs the open-weights release of MiniMax H3 Image (weights published by MiniMax). It edits an existing image from a text instruction: the first input image is the one being edited, and up to 8 more can be used as references, with up to 3 custom LoRA weights per request. Output is generated natively from 1k up to 4k.
3 LoRA weights in one request, each with its own scale.9 images, addressed as <Picture 1>, <Picture 2>, and so on.1k, 1.5k, 2k, 3k, or 4k; every tier is generated at its own size.| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Edit instruction describing the desired result. Refer to input images as <Picture 1>, <Picture 2>, and so on. |
| images | Yes | Between 1 and 9 image URLs. The first image is edited; additional images are used as references. |
| aspect_ratio | No | Output aspect ratio: 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 image's aspect ratio. |
| resolution | No | Output resolution: 1k, 1.5k, 2k, 3k, or 4k. Default: 1k. |
| output_format | No | Output format: jpeg, png, or webp. Default: jpeg. |
| loras | No | Up to 3 LoRA weights. Each item uses {path, scale}, where path points to the LoRA file and scale controls its influence. |
| seed | No | Random seed. Use -1 for random generation. |
Pricing is based on the selected resolution, with a fixed $0.015 LoRA surcharge per generation included in the table.
The first input image is included in the base price. Each additional input image costs $0.01.
| Resolution | Base Price |
|---|---|
| 1K | $0.045 |
| 1.5K | $0.06 |
| 2K | $0.075 |
| 3K | $0.135 |
| 4K | $0.195 |
| Additional Reference Images | Additional Cost |
|---|---|
| 1 | +$0.01 |
| 4 | +$0.04 |
| 8 | +$0.08 |
Aspect ratio, output format, and seed do not add separate charges.
prompt and images are required.images supports between 1 and 9 inputs; the first is the image being edited.resolution defaults to 1k; output_format defaults to jpeg.seed=-1 for random seed selection.3 LoRA weights per request, each as {path, scale}.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3-image/edit-lora with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Minimax H3 Image Edit Lora below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3-image/edit-lora" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3-image/edit-lora";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/minimax-h3-image/edit-lora", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Minimax H3 Image Edit Lora is a WaveSpeedAI model for image editing, exposed as a REST API on WaveSpeedAI. MiniMax H3 Image, the open-weights release of MiniMax's image model, edits images from natural-language instructions with up to 9 input images and custom LoRA weights, native output from 1K to 4K. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/minimax-h3-image-edit-lora.
Minimax H3 Image Edit Lora starts at $0.03 per run or per second. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `images`, `aspect_ratio`, `resolution`, `seed`, `loras`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/minimax-h3-image-edit-lora.
Reported generation time on WaveSpeedAI is around 53 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.