Early Model Versions
- DarkLight
Early Model Versions
- DarkLight
Article summary
Did you find this summary helpful?
Thank you for your feedback
Midjourney regularly introduces new model versions to improve coherency, efficiency, quality, and style. You can switch model versions by using the /settings command and selecting your preferred model version. Different models excel at producing different types of images.
Read about the latest Midjourney Models here
Model Version 1, 2, and 3 (Legacy)
You can access earlier midjourney models by using the --version or --v parameter or by using the /settings command and selecting a model version. Different models excel at different types of images.
prompt example: /imagine prompt vibrant California poppies --v 1
--version 3
default model: 07/22–11/22
highly creative compositions
moderate coherency
--version 2
default model: 04/22–07/22
creative, colorful, and painterly
low coherency
--version 1
default model: 02/22–04/22
very abstract and painterly
low coherency
--hd (high definition)
early alternative model
busy detailed and abstract
low coherency
Niji Model 4 (Legacy)
The niji 4 model is a collaboration between Midjourney and Spellbrush tuned to produce anime and illustrative styles. The --niji 4 model has vastly more knowledge of anime, anime styles, and anime aesthetics. It's excellent at dynamic and action shots and character-focused compositions in general.
prompt example: /imagine prompt vibrant California poppies --niji 4
--v 4
California poppies --v 4
--niji 4
California poppies --niji 4
--v 4
birds sitting on a twig --v 4
--niji 4
birds sitting on a twig --niji 4
Test Models (Legacy)
Occasionally new models are released temporarily for community testing and feedback. There are currently two available test models: --test and --testp, which can be combined with the --creative parameter for more varied compositions.
prompt example: /imagine prompt vibrant California poppies --testp --creative
--test
A general-purpose artistic model with good coherency
--test + --creative
--testp
A photo-realism model with good coherency
--testp + --creative
Notes on current test models
--test and --testpTest models only support --stylize values between 1250–5000.
Test models do not support multi-prompts or image-prompts
Test models have a maximum aspect ratio of 3:2 or 2:3.
Test models only generate two initial grid images when the aspect ratio is 1:1.
Test models only generate one initial grid image when the aspect ratio is not 1:1.
Words near the front of the prompt may matter more than words near the back.
Early Model Upscaler Tools
Earlier Midjourney model versions start by generating a grid of low-resolution image options for each Job. You can use a Midjourney upscaler on any of these images to increase the size and add additional details. There are multiple upscale models available for upscaling an image. Using an upscaler uses your subscription's GPU minutes.
The U1 U2 U3 U4 buttons under each image grid are used to upscale the selected image.
Read more about current upscaling options
Midjourney Dimensions and Sizes
All sizes are for square 1:1 aspect ratios.
| Model Version | Starting Grid Size | V4 Default Upscaler | Detail Upscale | Light Upscale | Beta Upscale | Max Upscale** |
|---|---|---|---|---|---|---|
| v1–v3 | 256 x 256 | - | 1024 x 1024* | 1024 x 1024 | 1024 x 1024 | 1664 x 1664 |
| niji | 512 x 512 | 1024 x 1024 | 1024 x 1024 | 1024 x 1024 | 2048 x 2048 | - |
| test / testp | 512 x 512 | - | - | - | 2048 x 2048 | - |
| hd | 512 x 512 | - | 1536 x 1536* | 1536 x 1536 | 2048 x 2048 | - |
* = the default upscaler for each Midjourney Version Model.
** Max Upscale is an older resource-intensive upscaler and is only available when users are in Fast Mode.
Light Upscaler
The Light Upscaler creates a 1024px x 1024px image and adds a moderate amount of details and textures. The Light Upscaler is useful for faces and smooth surfaces when using older Midjourney Model Versions.
Use the --uplight parameter to change the behavior of the U1 U2 U3 U4 upscale buttons to use the Light Upscaler.
prompt: adorable rubber duck medieval knight
prompt: sand cathedral
Detailed Upscaler
The Detail Upscaler creates a 1024px x 1024px image and adds many additional fine details to the image.
Images that have been upscaled with the detailed upscaler can be upscaled again using the Upscale to Max button for a final resolution of 1664px x 1664px. Upscale to Max is only available when in Fast mode.
The Detailed upscaler was the default for Midjourney Model Versions V1, V2, V3, and hd
prompt: adorable rubber duck medieval knight
prompt: sand cathedral
Beta Upscaler
The Beta Upscaler creates a 2048px x 2048px image without adding many additional details. The Beta Uspcaler is useful for faces and smooth surfaces.
Use the --upbeta parameter to change the behavior of the U1 U2 U3 U4 upscale buttons to use the Beta Upscaler.
prompt: adorable rubber duck medieval knight
prompt: sand cathedral
