Model Versions
Last updated
Last updated
The Midjourney V5.2 model is the newest and most advanced, released June 2023. To use this model, add the --v 5.2 parameter to the end of a prompt, or use the /settings command and select 5️⃣ MJ Version 5.2
This model produces more detailed, sharper results with better colors, contrast, and compositions. It also has a slightly better understanding of prompts than earlier models and is more responsive to the full range of the --stylize parameter.
Prompt: vibrant California poppies --v 5.2
Prompt: high contrast surreal collage --v 5.2
Midjourney Model Versions 5.1 and 5.2 can be fine-tuned with the --style raw parameter to reduce Midjourney default aesthetic.
Read more about the Midjourney --style parameter.
default --v 5.2
vibrant California poppies
--v 5.2 --style raw
vibrant California poppies --style raw
default --v 5.2
high contrast surreal collage
--v 5.2 --style raw
high contrast surreal collage --style raw
The Midjourney V5.1 was released on May 4th, 2023. To use this model, add the --v 5.1 parameter to the end of a prompt, or use the /settings command and select 5️⃣ MJ Version 5.1
This model has a stronger default aesthetic than earlier versions, making it easier to use with simple text prompts. It also has high Coherency, excels at accurately interpreting natural language prompts, produces fewer unwanted artifacts and borders, has increased image sharpness, and supports advanced features like repeating patterns with --tile.
Prompt: vibrant California poppies --v 5.1
Prompt: high contrast surreal collage --v 5.1
The Midjourney V5 model produces more photographic generations than the default 5.1 model. This model produces images that closely match the prompt but may require longer prompts to achieve your desired aesthetic.
To use this model, add the --v 5 parameter to the end of a prompt, or use the /settings command and select 5️⃣ MJ Version 5
Prompt: vibrant California poppies --v 5
Prompt: high contrast surreal collage --v 5
The Midjourney V4 was the default model from Nov 2022–May 2023. This model featured an entirely new codebase and brand-new AI architecture designed by Midjourney and trained on the new Midjourney AI supercluster. Model Version 4 had increased knowledge of creatures, places, and objects compared to previous models.
This model has very high Coherency and excels with Image Prompts.
Prompt: vibrant California poppies
Prompt: high contrast surreal collage
The Niji model is a collaboration between Midjourney and Spellbrush tuned to produce anime and illustrative styles with vastly more knowledge of anime, anime styles, and anime aesthetics. It's excellent at dynamic and action shots and character-focused compositions.
To use this model, add the --niji 5 parameter to the end of a prompt, or use the /settings command and select 🍏 Niji version 5
This model is sensitive to the --stylize parameter. Experiment with different stylization ranges to fine-tune your images.
Niji Model Version 5 can also be fine-tuned with --style parameters to achieve unique looks. Try --style cute, --style scenic, --style original (uses the original Niji Model Version 5, which was the default before May 26th, 2023), or --style expressive.
default --niji 5
birds perching on a twig --niji 5
--style original
birds perching on a twig --niji 5 --style original
--style cute
birds perching on a twig --niji 5 --style cute
--style expressive
birds perching on a twig --niji 5 --style expressive
--style scenic
birds perching on a twig --niji 5 --style scenic
--v 5.2
vibrant California poppies
--niji 5
vibrant California poppies --niji 5
--v 5.2
birds sitting on a twig
--niji 5
birds sitting on a twig --niji 5
Add --v 4 --v 5 --v 5.1 --v 5.1 --style raw --v 5.2 --v 5.2 --style raw --niji 5 --niji 5 --style cute --niji 5 --style expressive --niji 5 --style original or --niji 5 --style scenic to the end of your prompt.
Type /settings and select your preferred version from the menu.
4️⃣ MJ Version 4 5️⃣ MJ Version 5 5️⃣ MJ Version 5.1 5️⃣ MJ Version 5.2 🍎 Niji Version 5
You can experiment with early Midjourney models using the --version parameter Read more about Midjourney Legacy Models.
Coherency is the strength of the connection between the text prompt and the resulting image. A high degree of coherency means that the image will be an accurate representation of the prompt text.
Coherency is the strength of the connection between the text prompt and the resulting image. A high degree of coherency means that the image will be an accurate representation of the prompt text.
