Midjourney generates polished, highly stylized images from text prompts with aspect ratio, HD detail, render quality, stylize, chaos, weird, seed, and style-reference controls. It does not expose an exact pixel-size or 2K selector.
Added Jun 19, 2026
Approx. Price
$0.100 per image
Model Type
text-to-image
Settings
Generation controls available for this model.
Images Per Run
Fixed 4
Output images
Input Images
N/A
No reference/edit image input
Output Sizes
Aspect Ratio
Default
1:1
Chaos
Default
0
How varied and unexpected the output should be.
HD detail mode
Default
No
Use Midjourney HD detail mode: $0.15 per four-image request instead of $0.10. Disabled for v7. This does not select an exact pixel resolution.
Number of Images
Default
4
Render quality
Default
1
Options (2)
1 (normal), 4 (more detail)
Midjourney render quality (detail level). This is not a pixel-resolution selector.
Resolution
Default
1:1
Options (9)
1:1 (Square), 16:9 (Landscape (16:9)), 9:16 (Portrait (9:16)), 21:9 (Cinematic wide (21:9)) +5 more
Seed
Default
N/A
Random seed for reproducible generation. Leave empty for random.
Style Reference URL
Default
N/A
Optional public image URL used as a style reference.
Stylize
Default
0
How strongly Midjourney applies its default aesthetic.
Showing 9 of 11 settings.
Benchmarks
Benchmarks
No benchmark data is available yet for this model.
Examples
Loading examples…
Related image models
Compare Midjourney with similar models from the same provider or model family.
Qwen Image 2.1 Edit
wavespeed-ai/qwen-image-2.1/editEdit from up to ten reference images with natural-language instructions, strong subject preservation, flexible framing, and native output up to 2K.
Qwen Image 2.1 Edit LoRA
wavespeed-ai/qwen-image-2.1/edit-loraEdit from up to ten references while applying up to three custom LoRAs for precise identity, product, or style control at up to 2K.
Qwen Image 2.1
wavespeed-ai/qwen-image-2.1/text-to-imageCreate high-quality images with strong prompt following, multilingual text rendering, flexible framing, and native output up to 2K.
Qwen Image 2.1 LoRA
wavespeed-ai/qwen-image-2.1/text-to-image-loraGenerate Qwen Image 2.1 artwork with up to three custom character, product, or style LoRAs and native output up to 2K.
Bria Product Holding
bria/product-holdingPlace one to three referenced products naturally into a person's hands while preserving the subject and scene. Built for e-commerce, lifestyle advertising, influencer content, and product campaigns.
Bria Virtual Try-On
bria/virtual-try-onDress a person in one to three referenced garments or accessories while preserving their identity and pose. Built for virtual try-on, fashion catalogs, styling, and e-commerce previews.