Midjourney Text-to-Image creates high-quality, artistic images from text prompts, with strong creative interpretation, detailed composition, and flexible visual styles for concept art, marketing assets, social content, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle




$0.1per run·~10 / $1

A photorealistic fashion portrait of an adult woman standing in a room filled with tall mirrors, wearing a silver satin dress, multiple reflections around her, soft studio lighting, elegant mysterious expression, luxury editorial photography, cinematic composition, ultra-detailed, no text

ultra-realistic, cinematic lighting, soft focus, aesthetic composition, delicate details, beautiful color grading, serene atmosphere, masterpiece photography style, elegant and poetic feeling .

A lone, heavily armored knight made of stained glass, standing guard at the shattered gate of a crystal palace floating in a void of swirling galaxies. Cracks in the glass armor leak faint, colorful light. Dramatic low-angle shot, octane render, volumetric nebula lighting, sense of duty and loss.

ultra-realistic, cinematic lighting, soft focus, aesthetic composition, delicate details, beautiful color grading, serene atmosphere, masterpiece photography style, elegant and poetic feeling — add the text “MJ” subtly in the bottom right corner of the image

Cinematic action frame capturing the climax of a wizard duel. Two mages, one cloaked in shadow wielding green necrotic energy, the other in white robes wielding golden divine light, clash their spells in the center of a crumbling cathedral interior. Sparks, debris, and magical particles explode outwards. Dynamic Dutch angle, motion blur, high fantasy art, style of Magic the Gathering illustration.

Cinematic establishing shot for a sci-fi film. Ultra-wide angle view of a colossal, ancient alien derelict spaceship half-buried in the crimson sands of a desolate desert planet under twin suns. Tiny human explorers in white suits stand near its base for scale. Golden hour lighting, atmospheric dust, photorealistic matte painting, style of Denis Villeneuve.

Surreal cinematic shot. A fully furnished, vintage living room (armchair, lamp, bookshelf) is completely submerged underwater. Sunlight filters down from the surface, creating rippling caustic patterns on the furniture. A lone figure in a flowing white dress floats peacefully in the center of the room. Ethereal, dreamlike atmosphere, photorealistic, style of Gregory Crewdson.
Midjourney Text-to-Image generates images from a text prompt. Describe the image you want, optionally add a style reference image, choose an aspect ratio, and adjust generation controls such as HD mode, quality, stylize, chaos, weird, and seed.
Prompt-based image generation
Generate images directly from a text prompt.
Style reference support
Use an optional style reference image to guide the visual style of the generated images.
Flexible aspect ratios
Choose from multiple output aspect ratios, including square, vertical, horizontal, and cinematic formats.
Generation control parameters
Adjust stylize, chaos, and weird to control aesthetic strength, variation, and unconventional visual characteristics.
HD mode
Enable hd when you want higher-definition generation.
Seed support
Use a fixed seed for more reproducible results, or set -1 for a random seed.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text prompt describing the image to generate. Maximum length: 1024 characters. |
| sref | No | Optional style reference image URL. |
| aspect_ratio | No | Aspect ratio of the generated images. Options: 1:1, 9:16, 16:9, 4:3, 3:4, 2:3, 3:2, 9:21, or 21:9. Default: 1:1. |
| hd | No | Enable HD generation mode. Default: false. |
| quality | No | Generation quality setting. Options: 1 or 4. Default: 1. |
| stylize | No | Controls how strongly the model's aesthetic style influences the result. Range: 0–1000. Default: 0. |
| chaos | No | Controls variation and unpredictability. Range: 0–100. Default: 0. |
| weird | No | Adds unconventional or surreal characteristics. Range: 0–3000. Default: 0. |
| seed | No | Random seed. Use -1 for a random seed. Range: -1–2147483647. Default: -1. |
sref if you want to guide the visual style with a reference image.1:1, 9:16, 16:9, or 21:9.hd when higher-definition generation is needed.quality, stylize, chaos, weird, and seed as needed.Returns generated image URL(s) in the standard WaveSpeed prediction response.
Each request generates 4 images.
Pricing is based on whether hd is enabled. Each request generates 4 images.
| HD Mode | Request Cost | Effective Cost per Image |
|---|---|---|
false | $0.10 | $0.025 |
true | $0.15 | $0.0375 |
Other parameters do not add separate charges.
sref, stylize, chaos, and weird to test different visual directions.16:9, 21:9, 9:16, or 9:21 for different content formats.sref when you want the output to follow a specific visual style.stylize to control the strength of the model's aesthetic influence.chaos when you want more variation across outputs.weird when you want more unconventional or surreal results.hd when higher-definition output is needed.seed when you want more reproducible generations.-1 for random seed generation.1:1 for square images, 9:16 for vertical content, or 16:9 for widescreen images.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/midjourney/text-to-image with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Text To Image below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"hd": false,
"quality": 1,
"stylize": 0,
"chaos": 0,
"weird": 0
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/midjourney/text-to-image" \
-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/midjourney/text-to-image";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"hd": false,
"quality": 1,
"stylize": 0,
"chaos": 0,
"weird": 0
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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",
"aspect_ratio": "1:1",
"hd": False,
"quality": 1,
"stylize": 0,
"chaos": 0,
"weird": 0
}
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/midjourney/text-to-image", 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)Text To Image is a Midjourney model for image generation, exposed as a REST API on WaveSpeedAI. Midjourney Text-to-Image creates high-quality, artistic images from text prompts, with strong creative interpretation, detailed composition, and flexible visual styles for concept art, marketing assets, social content, and production workflows. 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 production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/midjourney/midjourney-text-to-image.
Text To Image starts at $0.10 per run. 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`, `aspect_ratio`, `seed`, `chaos`, `hd`, `quality`. 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/midjourney/midjourney-text-to-image.
Median end-to-end generation time on WaveSpeedAI is around 28 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Midjourney). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.