Model Information

Complete guide to Midjourney model versions including v6, v6.1, v7, and niji 6 - features, capabilities, and parameter support for each version

The API provides multiple model version options covering the v6 series, v7 series, and niji series. Each model version has unique advantages in image generation quality, feature characteristics, and parameter support.

Supported Models: The API currently supports models v6, v6.1, niji 6, v7, and v8, with v7 as the default.

Version 8 🆕

Version 8 (alpha launched March 17, 2026) is a generational leap in AI image generation. Add --v 8 to your prompt to use it.

Key Improvements

• ~5x faster generation: Standard images complete in under 15 seconds
• Native 2K HD resolution: Use --hd for natively rendered 2K images — no upscale needed
• Dramatically better text rendering: Wrap text in "quotes" for readable signs, labels, and typography
• Accurate hands & anatomy: Correct finger counts, natural proportions, consistent full-body poses
• Superior prompt adherence: Complex multi-element compositions render with much higher fidelity
• Enhanced coherence: --q 4 mode maintains visual consistency in complex scenes
• Physically accurate lighting: Reflections, subsurface scattering, and shadow direction are physically grounded

V8 Parameters

• --hd — Native 2K resolution (4x cost)
• --q 4 — Enhanced coherence mode (4x cost)
• --oref — Omni Reference, replaces --cref (handles both person likeness and object form)
• --sv 6 — Use old (more accurate) SREF version (4x cost)
• All V7 parameters (--chaos, --weird, --exp, --raw, --sref, --stylize, etc.) are supported

V8 Cost Model

• Standard V8 generation: same cost as V7
• Premium features (--hd, --q 4, --sv 6): 4x cost
• V8 does not require upscaling — images are natively high resolution
• Turbo mode (--turbo) is not supported with V8

Feature Support

Feature	v7	v8
Variation	Strong & Subtle	Strong & Subtle
Upscale	Subtle & Creative	Not needed (native 2K)
Reroll	✓	✓
Remix	✓	✓
Animate (image to video)	✓	✓
Blend	✓	✓ (V8 native)
Inpaint / Outpaint / Pan	✓	Not available
Style Reference (—sref)	✓	✓ (higher fidelity)
Personalization (—p)	✓	✓ (backward compatible)

Version 7

Version 7 (released April 3, 2025) achieved significant breakthroughs in image generation. This version dramatically improved the processing accuracy of text and image prompts, while achieving a qualitative leap in image quality—particularly in human anatomy, hand details, and object textures.

As core innovations, V7 introduces two revolutionary features:

• Draft Mode: Supports rapid iterative generation
• Universal Reference: Provides more powerful image reference capabilities, bringing new possibilities to creative workflows

Feature Support

Feature	v6*	v7*
Variation	Strong & Subtle	Strong & Subtle
Upscale	Subtle & Creative	Same as v6.1
Extend	✓	Same as v6.1
Outpaint	✓	Same as v6.1
Reshape	✓	✓
Moodboard	✓	✓
Edit	✓	Same as v6.1
Advanced Edit	✓	✓

The quality parameter in V7 works differently. Please refer to the [Quality Parameter Documentation] for details.

Version 6.1

Version 6.1 was released on July 30, 2024, as the current default model. It generates images with more coherent effects, more precise details and textures, and is approximately 25% faster than version 6.

Version 6

Version 6 was released on December 20, 2023, and served as the default model from February 14 to July 30, 2024. Version 6 enhanced prompt accuracy for longer inputs, improved coherence and knowledge, and provided advanced image prompting and mixing capabilities.

Niji 6

The Niji model is a special series within the platform, developed in collaboration with Spellbrush, focusing on Eastern and anime aesthetics and illustration styles.

Niji 6 was released on June 7, 2024, with improved Japanese text rendering capabilities, efficient processing of short Japanese text, and even the ability to render simple Chinese characters. It provides better image details, particularly in elements like anime eye structures, and resolves some minor image defects that affected a small portion of previously generated images.

Model Parameter Comparison

The following table provides a detailed comparison of the parameters supported by each model version and their value ranges:

Parameter	v6	v6.1	v7	v8	niji 6	Video Model
Original Mode	raw	raw	raw	raw	raw	raw
Tile	true/false	true/false	true/false	true/false	true/false	🚫
Chaos	0-100	0-100	0-100	0-100	0-100	🚫
Seed	0-4294967295	0-4294967295	0-4294967295	0-4294967295	0-4294967295	🚫
Stop	10-100	10-100	10-100	🚫	10-100	🚫
Weird	0-3000	0-3000	0-3000	0-3000	0-3000	🚫
Stylize	0-1000	0-1000	0-1000	0-1000	0-1000	🚫
Quality	(1, 2)	(0.5, 1, 2)	(1, 2, 4)	(1, 4)	(0.5, 1, 2)	🚫
HD Mode	🚫	🚫	🚫	✓ (4x cost)	🚫	🚫
Fast Mode	✓	✓	✓	✓	✓	✓
Turbo Mode	✓	✓	✓	🚫	✓	✓
Relax Mode	🚫	🚫	🚫	🚫	🚫	🚫
Image Weight	0-3	0-3	0-3	0-3	0-3	🚫
Negative Prompt	🚫	✓	✓	✓	🚫	🚫
Style Reference	✓	✓	✓	✓	✓	🚫
Omni Reference (—oref)	🚫	🚫	✓	✓	🚫	🚫
Character Reference (—cref)	✓	✓	✓	Replaced by —oref	✓	🚫
Style Version (—sv)	(1, 2, 3, 4)	(1, 2, 3, 4)	(1, 2, 3, 4)	6 (legacy, 4x cost)	(1, 2, 3, 4)	🚫
Style Weight	0-1000	0-1000	0-1000	0-1000	0-1000	🚫
Draft	🚫	🚫	✓	🚫	🚫	🚫
Experimental	🚫	🚫	0-100	✓	🚫	🚫
Personalization (—p)	🚫	🚫	✓	✓ (V7 compatible)	🚫	🚫
Upscale	Subtle & Creative	Subtle & Creative	Subtle & Creative	Not needed (native 2K)	Subtle & Creative	🚫

Notes:

1. ✓ indicates support for this parameter 🚫 indicates no support for this parameter
2. v8 model: --hd renders natively at 2K resolution (no upscale needed). --hd, --q 4, and --sv 6 each cost 4x credits. Turbo mode is not supported.
3. v7 model exclusive parameters: draft (Draft Mode), oref (Universal Reference), ow (Universal Reference Weight), and exp (Experimental Parameters)
4. v8 replaces --cref (Character Reference) with --oref (Omni Reference) which handles both person likeness and object form
5. Video model exclusive parameters: video (Video Mode), motion (Motion Mode), end (Video End Frame), and loop (Video Loop)
6. v6.1, v7, and v8 models support the no parameter (negative prompts)