Skip to main content
AI image model
Midjourney
Midjourney

Midjourney

Kyeo's Midjourney page generates from text or up to four reference images, with three speeds, seven aspect ratios, and five V7, V6, or Niji versions. It is not a full mirror of Midjourney's product: Midjourney now defaults to V8.1, while Kyeo still defaults to V7 and exposes no Style Reference, Omni Reference, or video workflow.

Online use is currently unavailable

This page is for reviewing the model's capabilities, use cases, and public references. The model does not appear in the home workbench and cannot submit generation tasks.

Capabilities
Text-to-Image, Image-to-Image
Credit cost
3-16 credits per request; Fast pricing depends on image uploads
Prompt limit
2,000 characters
Upload limit
4 images
Calls only `mj_txt2img` or `mj_img2img`, not Midjourney's full editing, reference, and video toolset.
Exposes `speed`, `aspectRatio`, and `version`, with up to four uploads for image-guided generation.
Relaxed costs 3 credits; Fast costs 8 for text or 6 with images; Turbo costs 16.
Kyeo defaults to V7; Midjourney's current default V8.1 is not an available version.
30-second overview
Midjourney
Currently unavailable
What it does best
It does not represent Midjourney's current V8.1 product, editor, or complete parameter set.
Best for
It fits visual-direction tests for posters, covers, illustrations, characters, and world concepts, plus same-prompt comparisons across V7, V6.1, and Niji 7.
Popular searches
how to use Midjourneyhow many credits does Midjourney use on KyeoMidjourney Relaxed vs Fast vs Turbo

At a glance

What is this model like?

A prompt of up to 2,000 characters uses `mj_txt2img` when no image is present and switches to `mj_img2img` with one to four uploads. Credits range from 3 for Relaxed to 16 for Turbo, while Fast costs 8 for text generation and 6 when an image is uploaded.

What it does best
It does not represent Midjourney's current V8.1 product, editor, or complete parameter set.
Best for
It fits visual-direction tests for posters, covers, illustrations, characters, and world concepts, plus same-prompt comparisons across V7, V6.1, and Niji 7.
Why use it on Kyeo AI
Kyeo combines text and reference-image entry points and surfaces the `speed`, `aspectRatio`, and `version` values it sends, along with the resulting credit cost.

Key facts

Quickly assess whether this model matches your workflow.

Category
AI image model
Vendor
Midjourney
Model family
Midjourney
Integration
Current site integration
Platform model ID
midjourney
Runtime
Asynchronous task
Prompt limit
2,000 characters
Upload limit
4 images

Also known as

The same model may appear under different names across documentation and community discussions; this list keeps them easy to search and compare.

midjourney
Midjourney V7
MJ
Niji 7

Common search intents

These questions and keywords combine public references with common creative use cases to help you choose faster.

how to use Midjourney
how many credits does Midjourney use on Kyeo
Midjourney Relaxed vs Fast vs Turbo
does Kyeo Midjourney support V8.1
Midjourney V7 or Niji 7
which aspect ratios does Kyeo Midjourney support
how many images can Kyeo Midjourney use
does Kyeo Midjourney support Omni Reference
does Kyeo Midjourney support Style Reference
Midjourney or Nano Banana Pro
Midjourney or Flux 2 Pro
how to choose Midjourney reference images

Selection guide

Use these decision points when choosing a model.

1
Choose it to compare Midjourney and Niji directions

Use the same brief across V7, V6.1, and Niji 7 when the task is to evaluate composition, mood, subject interpretation, or a more illustration-oriented treatment.

2
Compare another model for explicit edits or character reference

Compare Nano Banana Pro or Flux 2 Pro for prompt-led changes to an existing image, and Ideogram Character when one subject's recognizability across scenes is the core review.

3
Verify the workflow before running controlled comparisons

Then hold V7 and 1:1 constant to compare speed; for a version test, hold the prompt and `speed` constant and switch only to V6.1 or Niji 7.

Popular comparisons

Common comparison questions help you find the practical differences quickly.

What is the difference between Midjourney and Nano Banana Pro?
Midjourney versus Nano Banana Pro
What is the difference between Midjourney and Flux 2 Pro?
Midjourney versus Flux 2 Pro
What is the difference between Midjourney and Ideogram Character?
Midjourney versus Ideogram Character

Model comparison

Compare the current model with alternatives at a glance.

Dimension
Midjourney
Nano Banana Pro
Flux 2 Pro
Current workflow
Text-to-Image, or visual guidance from 1-4 images
Generation and editing with up to 8 reference images
Generation from text or up to 8 reference images
Page controls
`speed`, `aspectRatio`, and `version`
`resolution`, `aspect_ratio`, and `output_format`
Fixed ratios and `1K / 2K` output
Reference-image boundary
Up to 4 images, without weight, Omni, or Style Reference controls
Up to 8 images for prompt-led generation or editing
One character reference, reviewed for recognizability
Credits per request
Relaxed 3; Fast text 8 / image 6; Turbo 16
1K/2K 8; 4K 14
1K 5; 2K 7
Primary review target
Composition, mood, subject interpretation, and reference influence
Prompt execution, reference influence, and output size
Face, hair, clothing, and signature details

Practical usage insights

Practical observations based on real creative workflows.

Midjourney's default moved on; Kyeo's version list did not

Midjourney made V8.1 its default in June 2026, while Kyeo's highest general version remains V7.

Kyeo credits and Midjourney GPU time are separate systems

Kyeo charges credits per request. Midjourney describes GPU time within its own subscriptions.

The legacy workflow remains in code after its public docs disappeared

Release readiness must come from a live workflow check, not a historical schema. Technical identifiers: `/mj/generate`.

Capabilities

Separate text and reference-image paths

Without an image, Kyeo sends `mj_txt2img`. With one to four uploads, it sends `mj_img2img` and `fileUrls`. Both paths require a prompt of no more than 2,000 characters.

Three speeds, seven ratios, and five versions

The options are Relaxed, Fast, and Turbo; 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3; and V7, V6.1, V6, Niji 7, and Niji 6. Defaults are relaxed, 1:1, and V7.

Speed and input path determine credits

Relaxed and Turbo cost 3 and 16 credits regardless of uploads. Fast costs 8 for Text-to-Image and 6 for Image-to-Image. A speed label is not a fixed latency promise.

No role or weight controls for reference images

Kyeo places every upload in `fileUrls` without image weight, Style Reference, Omni Reference, or related weighting controls. Test whether any person, object, or style survives the transformation.

Use cases

Poster and cover concepts

Explore composition, color, and mood from a text brief, then review text, subject details, and layout before using an output in design work.

Same-brief V7 and Niji comparison

Hold the prompt, ratio, and speed steady across V7, V6.1, and Niji 7 to compare a general image treatment with Niji's animation and illustration focus.

Mood-board and sketch guidance

Upload one to four mood boards, composition sketches, or visual assets and inspect their influence. Without individual weights, each additional image makes attribution harder.

Prompt tips

Fix version, ratio, and speed first

Change only the prompt in the first round. If version, aspectRatio, and speed all move at once, the cause of any visual difference is unclear.

Add reference images one at a time

Start with the single image that matters most, record how subject, composition, or color changes, and add another only when its contribution can be evaluated.

Keep style references separate from scene instructions

Relaxed, Fast, and Turbo primarily select Kyeo pricing and available scheduling. Hold the prompt and version constant when testing outputs.

Strengths

One page handles generation from text or up to four reference images.
V7, V6.1, V6, Niji 7, and Niji 6 support controlled version comparisons.
Seven fixed ratios cover common square, landscape, and portrait formats.
Credit differences across three speeds are visible before submission.

Limitations

Kyeo has no V8 or V8.1 option and exposes neither Omni Reference, Style Reference, video, nor most official parameters.
Kyeo currently offers V7, V6, and Niji options; review available versions periodically for long-lived workflows.
Four input images have no individual purpose or weight controls.
Review text, people, brand claims, trademarks, copyright, publicity rights, and advertising compliance before publication.

Adjustable parameters

Quickly assess whether this model matches your workflow.

Speed mode
speed
Optional
Parameter type: select
Default: relaxed
Relaxed (3 credits)
Fast (8 credits for Text-to-Image, 6 for Image-to-Image)
Turbo (16 credits)
Aspect ratio
aspectRatio
Optional
Parameter type: select
Default: 1:1
1:1
16:9
9:16
4:3
3:4
3:2
2:3
7 options
Model version
version
Optional
Parameter type: select
Default: 7
V7
V6.1
V6
Niji 7
Niji 6

FAQ

Related models

Compare these similar candidates before deciding.

Nano Banana Pro

Nano Banana Pro supports text-to-image generation and reference-image editing on Kyeo AI, with 1K, 2K, or 4K output. Each 1K or 2K request costs 8 credits, while 4K costs 14. Resolution is an output-size tier, not a guarantee of quality, accuracy, or detail.

AI image generation and editing model
8–14 credits per request

Flux 2 Pro

Flux 2 Pro on Kyeo supports text-to-image and image editing. A request without an upload uses `flux-2/pro-text-to-image`; attaching one to eight images switches to `flux-2/pro-image-to-image`. Both routes offer seven fixed aspect ratios and 1K/2K, currently priced at 5/7 credits.

AI image model
5-7 credits / request

Ideogram Character

Ideogram Character combines one character reference and a prompt to generate a new single image. It is built for testing whether a subject remains recognizable across scenes, poses, or compositions. Details can still drift, so consistency is a review target—not a guaranteed result.

AI image model
12-24 credits / request

Sources

Content is based on model documentation, feature references, and the settings available on Kyeo AI.

Source notes

Midjourney's official version, speed, and reference documentation defines the available scope. Kyeo exposes only `mj_txt2img`, `mj_img2img`, `speed`, `aspectRatio`, `version`, and up to four images. Midjourney now defaults to V8.1, while Kyeo still defaults to V7 and offers no V8 or V8.1 option.

Last reviewed: 2026-07-20
Midjourney Docs: Version
Official
View source
Midjourney Docs: GPU Speed (Fast, Relax, Turbo)
Official
View source
Midjourney Update: V8.1 is now the default model
Official
View source
Midjourney Docs: Omni Reference
Official
View source
Midjourney V7/Niji Kyeo integration notes
Platform

Historical Generate and Task Details schemas are not treated as proof of current availability. Technical identifiers: `llms.txt`.

Kyeo Midjourney request implementation
Platform

Kyeo still sends `taskType`, prompt, speed, aspectRatio, version, and optional fileUrls to the upstream interface's `/mj/generate`, then polls a dedicated status workflow. Live success and the response shape require a representative sample.

Kyeo AI model configuration
Platform

Kyeo offers Text-to-Image and Image-to-Image with a 2,000-character prompt, up to four images, and seven ratios. It defaults to V7 and omits Midjourney's current V8.1 default; pricing follows `speed` and upload presence.