Create high-quality, artistic images from text prompts using Midjourney's renowned creative interpretation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Siap
$0.1per run·~10 / $1
ContohLihat semua
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.
Model Terkait
README
Midjourney Text-to-Image
Midjourney Text-to-Image generates high-quality images from natural-language prompts with flexible aspect ratios, style controls, reference image guidance, and support for multiple Midjourney model versions. It is suitable for concept art, stylized visuals, cinematic imagery, anime-inspired art, and other prompt-driven image generation workflows.
Why Choose This?
-
Flexible Midjourney model versions Choose from
6,6.1,7, or8.1depending on your preferred look and behavior. -
Strong style control Fine-tune the result with
stylize,chaos, andweirdto balance coherence, creativity, and experimental output. -
Reference image support Use
srefto guide the generated image toward a desired visual direction. -
Aspect ratio control Supports square, portrait, landscape, and cinematic aspect ratios.
-
Optional HD generation Version
8.1supports optional native2kHD generation. -
Anime-focused mode Use
nijisettings when you want anime or Eastern-aesthetic results.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | The text prompt describing the image you want to generate. |
| sref | No | URL of the image to use as a style reference for generation. |
| aspect_ratio | No | Aspect ratio of the generated image. Supported values: 1:1, 9:16, 16:9, 4:3, 3:4, 2:3, 3:2, 9:21, 21:9. Default: 1:1. |
| quality | No | Controls image detail and processing time. Supported values: 0.25, 0.5, 1, 2. Default: 1. |
| stylize | No | Controls artistic styling strength. Range: 0–1000. Default: 0. |
| chaos | No | Adds variety and unpredictability to results. Range: 0–100. Default: 0. |
| weird | No | Makes the result more quirky or unconventional. Range: 0–3000. Default: 0. |
| version | No | Midjourney model version. Supported values: 6, 6.1, 7, 8.1. Default: 8.1. |
| hd | No | Enable native 2k HD generation for version 8.1. Default: false. |
| niji | No | Anime/Eastern-aesthetic mode selection. Supported values: 0, 5, 6, 7, close. Default: close. |
| seed | No | Seed for reproducibility. Use -1 for random generation. Default: -1. |
How to Use
- Write your prompt — describe the subject, style, lighting, mood, and composition you want.
- Choose aspect ratio — select the output framing that fits your use case.
- Set style controls (optional) — adjust
stylize,chaos, andweirdfor more artistic or experimental results. - Choose version — use the Midjourney version that best matches your workflow.
- Enable HD (optional) — turn on
hdif you are using version8.1and want higher-resolution output. - Add a reference image (optional) — use
srefwhen you want stronger style guidance. - Set seed (optional) — use
-1for random output, or a fixed seed for more reproducible results. - Submit — run the model and download the generated image.
Example Prompt
A cinematic sci-fi city street at night, neon reflections on wet pavement, dramatic fog, ultra-detailed architecture, moody lighting, dynamic composition
Pricing
Pricing is fixed per image, with an additional charge for HD generation on version 8.1.
| Mode | Cost |
|---|---|
| Standard generation | $0.10 |
Version 8.1 with hd=true | $0.15 |
Billing Rules
- Base price is $0.10 per image
- Enabling
hdadds a surcharge only whenversion = 8.1 version = 8.1withhd=truecosts $0.15 per imageaspect_ratio,quality,stylize,chaos,weird,niji,seed, andsrefdo not affect pricing
Best Use Cases
- Concept art — Explore visual directions for environments, characters, and products.
- Stylized illustration — Generate artistic, cinematic, or graphic compositions from text prompts.
- Anime-inspired imagery — Use
nijisettings for anime and Eastern-aesthetic outputs. - Marketing creatives — Produce eye-catching visuals for campaigns, ads, and presentations.
- Reference-guided ideation — Use
srefto push the output closer to a target style or mood.
Pro Tips
- Use
stylizewhen you want a stronger artistic interpretation. - Increase
chaoswhen you want more variation and less predictability. - Use
weirdsparingly when you want unusual or surreal results. - Only enable
hdwhen you need the extra resolution, since it increases cost. - Use
srefwhen style consistency matters more than purely prompt-based generation. - Keep
seedfixed when comparing prompt or parameter changes across runs.
Notes
promptis required.hdonly applies to version8.1.seed = -1means random generation.nijiis intended for anime and Eastern-style visual output.- Pricing is fixed per image, with a higher price only for
8.1HD generation.
Related Models
- Other Midjourney image generation workflows — Useful when you want different generation modes or prompt setups.
- Reference-guided image generation workflows — Useful when style steering from an image matters more heavily.
- Anime-focused image generation workflows — Useful when stylized illustration and character art are the main priority.
Text To Image API — Quick start
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; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Text To Image below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/midjourney/text-to-image" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"quality": 1,
"stylize": 0,
"chaos": 0,
"weird": 0,
"version": "8.1",
"hd": false,
"niji": "close",
"seed": -1,
"enable_base64_output": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("midjourney/text-to-image", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"quality": 1,
"stylize": 0,
"chaos": 0,
"weird": 0,
"version": "8.1",
"hd": false,
"niji": "close",
"seed": -1,
"enable_base64_output": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"midjourney/text-to-image",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"quality": 1,
"stylize": 0,
"chaos": 0,
"weird": 0,
"version": "8.1",
"hd": false,
"niji": "close",
"seed": -1,
"enable_base64_output": false
}
)
print(output["outputs"][0]) # → URL of the generated outputText To Image API — Frequently asked questions
What is the Text To Image API?
Text To Image is a Midjourney model for image generation, exposed as a REST API on WaveSpeedAI. Create high-quality, artistic images from text prompts using Midjourney's renowned creative interpretation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Text To Image API?
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 prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/midjourney/midjourney-text-to-image.
How much does Text To Image cost per run?
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.
What inputs does Text To Image accept?
Key inputs: `prompt`, `aspect_ratio`, `seed`, `chaos`, `enable_base64_output`, `hd`. 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.
How long does Text To Image take to generate?
Average end-to-end generation time on WaveSpeedAI is around 47 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Text To Image outputs commercially?
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.