Meticulous rendering of light, shadow, and texture
Accurately captures light, shading, and complex material details to reproduce visuals of high fidelity.
An image generation model combining artistic expressiveness and meticulous texture rendering. Efficiently create visuals in a wide variety of styles from text or reference images.
Each model has its own Playground, pricing, and field docs. Filter by capability to open the one you need.
Model id and a short note on what each capability is for.
| Model | ID | Description |
|---|---|---|
| Midjourney V8.1(text to image) | mj-image-v8.1-text-to-image | With overwhelming artistry and textural detail, it instantly transforms words into exquisite visuals. |
| Midjourney V8.1(image to image) | mj-image-v8.1-image-to-image | With overwhelming artistry and reproducibility, we elevate images to the finest visuals. |
With sophisticated light and shadow rendering and versatile style reproduction capabilities, it broadly supports creative production.
A magnificent mechanical world where gears and steam intertwine. A Victorian-era female inventor is immersed in her work.
Prompt
Inside a giant steampunk-style mechanical clock tower, filled with gears and steam pipes, a Victorian female inventor wearing a monocle is operating a complex device. Golden warm light and blue cold light intertwine, wit…

Generated with Midjourney V8.1

Generated with Midjourney NIJI 7

Generated with Midjourney V7
On a night of wet and cold rain, in the neon-lit future of Tokyo, a lonely girl merges with the light and shadows of technology.
Prompt
A cyberpunk-style rainy night in Tokyo's cityscape, with neon reflecting on the wet asphalt. A young Asian woman in a transparent raincoat stands under a street lamp, gazing down at her glowing smartphone. In the backgro…

Generated with Midjourney V8.1

Generated with Midjourney NIJI 7

Generated with Midjourney V7
A modern theater-style anime-inspired scene. In a lively street corner, two girls are happily taking selfies, creating a bright and cheerful atmosphere.
Prompt
The modern Japanese animated film style, of the highest quality, with vivid character depictions. A bustling Tokyo at noon, full of energy (with a pop atmosphere like Harajuku). Two young women are happily laughing and p…

Generated with Midjourney V8.1

Generated with Midjourney NIJI 7

Generated with Midjourney V7
Typical jobs this series is used for.
Depicts complex worldviews such as fantastical landscapes and sci-fi cities from natural language prompts, supporting visual design in the early planning stages.
Leveraging realistic texture rendering and strong text-rendering capabilities, it efficiently generates commercial images suitable for web banners, posters, and more.
Based on reference images, it can be flexibly adapted into different styles such as oil painting, watercolor, and cyberpunk.
Check production limits and starting credit cost before you pick another model for the same job.
| Model | Multimodal reference inputs | Max resolution | Sousaku starting price |
|---|---|---|---|
| Midjourney V8.1 | ❌ | Up to 1K | 2 Credits |
| Midjourney NIJI 7 | ❌ | Up to 1K | 2 Credits |
| Midjourney V7 | ❌ | Up to 1K | 2 Credits |
From sign-up to your first successful call. The same steps work for every model.
Sign up and verify so you can issue an API key and use Playground.
Open a card above to see that model's details, pricing, and field docs.
Confirm inputs and parameters in the form before you automate.
The field docs on the detail page list required parameters. Use the same names in create_task.
Call the generate API with your key, poll until the task succeeds, then download the result.
Track credit use on the model's pricing page and in the dashboard.
Other series on Sousaku. One API key, one task flow.