Image Battle
Compare AI Image Generators for your use-case
Head to head

Midjourney V6.1 vs MiniMax Image-01

By Elo rating, MiniMax Image-01 is expected to win 54% of comparisons against Midjourney V6.1.

Both models received the same prompts. Wins and losses count only images judged together in the same call, the same comparisons the leaderboard Elo is fitted from.

Midjourney V6.1
Midjourney
748 Elo ±37
Rank #38 of 42 · median 34s per image · 2 refused
Not judged in the same call yet
Elo expectation: Midjourney V6.1 wins 46%
MiniMax Image-01
Minimax
773 Elo ±52
Rank #37 of 42 · median 36s per image

By category

CategoryMidjourney V6.1MiniMax Image-01Direct record
Anime & Cartoon Style 853 695 —
Architecture & Interiors 816 758 —
Complex Scenes 626 699 —
Ghibli style 738 702 —
Graphic Design 688 776 —
Hands & Anatomy 715 804 —
Photorealistic People & Portraits 767 739 —
Surreal & Creative Prompts 680 685 —
Text in Images 792 845 —
Ultra Hard 621 885 —

By criterion

CriterionMidjourney V6.1MiniMax Image-01
Prompt adherence 732 774
Technical quality 834 867
Artistic merit 933 935
Detail execution 786 814
Realism & coherence 805 838

Side by side

Anime & Cartoon Style A 90s anime-style space battle scene with giant starships and laser beams.
A 90s anime-style space battle scene with giant starships and laser beams. - Midjourney V6.1
Midjourney V6.1 7 / 10 An artistically excellent anime dogfight, but a less complete interpretation of a giant-starship battle. Its scale ambiguity and occasional structural looseness keep it below the leading capital-ship scenes.
A 90s anime-style space battle scene with giant starships and laser beams. - MiniMax Image-01
MiniMax Image-01 6 / 10 Ranks ninth of twelve, with strong explosive spectacle and a confident large-scale composition. Its less specific anime styling and comparatively obscure spacecraft construction prevent it from joining the stronger entries.
Architecture & Interiors Photorealistic rendering of a contemporary glass skybridge between two skyscrapers, seen from inside with city views visible through glass walls and floor. Show accurate reflections and structural details.
Photorealistic rendering of a contemporary glass skybridge between two skyscrapers, seen from inside with city views visible through glass walls and floor. Show accurate reflections and structural details. - Midjourney V6.1
Midjourney V6.1 6 / 10 The image succeeds aesthetically but only partially communicates the requested transparent skybridge. It is more polished than the weaker examples, yet its floor treatment falls well behind the leading images.
Photorealistic rendering of a contemporary glass skybridge between two skyscrapers, seen from inside with city views visible through glass walls and floor. Show accurate reflections and structural details. - MiniMax Image-01
MiniMax Image-01 4 / 10 Rank 12 of 12: an appealing atmospheric image, but the least convincing architectural and optical interpretation. Unclear structural continuity and fragmented glazing substantially undermine the requested realism.
Complex Scenes A family cooking together in a kitchen, each person busy with a different task.
A family cooking together in a kitchen, each person busy with a different task. - Midjourney V6.1
Midjourney V6.1 5 / 10 Ranks thirteenth because believable, differentiated cooking tasks are the central weakness despite attractive artwork. The lower score reflects ambiguous interactions, not a penalty for using illustration instead of photography.
A family cooking together in a kitchen, each person busy with a different task. - MiniMax Image-01
MiniMax Image-01 6 / 10 Ranks tenth despite its exceptional atmosphere because it misses the prompt's central requirement of distinct active cooking tasks for everyone. Artistic strength raises it above a poor result, but cannot replace task clarity.
Ghibli style A countryside train station with a cat waiting on a bench. Rendered in Studio Ghibli animation style with Miyazaki's watercolor backgrounds and hand-drawn quality.
A countryside train station with a cat waiting on a bench. Rendered in Studio Ghibli animation style with Miyazaki's watercolor backgrounds and hand-drawn quality. - Midjourney V6.1
Midjourney V6.1 8 / 10 Ranks sixth as a consistently strong and coherent interpretation. Its heavier linework and less expressive cat keep it below the more atmospheric, character-focused leaders.
A countryside train station with a cat waiting on a bench. Rendered in Studio Ghibli animation style with Miyazaki's watercolor backgrounds and hand-drawn quality. - MiniMax Image-01
MiniMax Image-01 6 / 10 This ranks ninth: it is visually appealing and clearly depicts the requested situation, but the stylistic deviation is substantial. Its polished fantasy-pet aesthetic outweighs otherwise competent rendering when judged against the specific watercolor-animation request.
Graphic Design Minimalist logo for a sustainable coffee brand 'Evergreen Brew', single leaf motif, clean lines, vector style, white background. 'Evergreen Brew' contained as text in logo
Minimalist logo for a sustainable coffee brand 'Evergreen Brew', single leaf motif, clean lines, vector style, white background. 'Evergreen Brew' contained as text in logo - Midjourney V6.1
Midjourney V6.1 3 / 10 Ranks thirteenth because the required brand text is absent and the single-leaf instruction is violated. Clean rendering cannot compensate for failing these central requirements.
Minimalist logo for a sustainable coffee brand 'Evergreen Brew', single leaf motif, clean lines, vector style, white background. 'Evergreen Brew' contained as text in logo - MiniMax Image-01
MiniMax Image-01 6 / 10 Rank 8 of 12: aesthetically competent, but its attractive abstraction weakens adherence to the single-leaf requirement. It trails the clearer, more economical botanical marks.
Hands & Anatomy A yoga practitioner in a complex pose, arms and legs fully extended (full-body view).
A yoga practitioner in a complex pose, arms and legs fully extended (full-body view). - Midjourney V6.1
Midjourney V6.1 5 / 10 Ranked 11th: this is an expressive painting but a weak solution to the defining pose requirement. Folded legs and reduced anatomical precision outweigh its strong stylistic execution.
A yoga practitioner in a complex pose, arms and legs fully extended (full-body view). - MiniMax Image-01
MiniMax Image-01 2 / 10 This is the weakest image because its central figure cannot be reconciled with normal human anatomy. Attractive lighting provides limited value when the requested practitioner is fundamentally malformed.
Photorealistic People & Portraits A group selfie of three friends of different ethnic backgrounds smiling at the camera.
A group selfie of three friends of different ethnic backgrounds smiling at the camera. - Midjourney V6.1
Midjourney V6.1 8 / 10 Rank 6 of 13: this is one of the most naturally textured images and communicates warmth very effectively. Its restrictive crop and less explicit selfie construction keep it behind the top travel and street examples.
A group selfie of three friends of different ethnic backgrounds smiling at the camera. - MiniMax Image-01
MiniMax Image-01 7 / 10 An attractive, competent selfie with strong warmth and clear prompt coverage. Noticeable beauty-style processing and reduced shadow detail prevent it from matching the more naturally photographic candidates.
Surreal & Creative Prompts A city skyline that forms the shape of musical notes on a staff, created in a stylized graphic design aesthetic with clean architectural lines and dramatic twilight colors.
A city skyline that forms the shape of musical notes on a staff, created in a stylized graphic design aesthetic with clean architectural lines and dramatic twilight colors. - Midjourney V6.1
Midjourney V6.1 5 / 10 Ranked 10 of 13. Its distinctive palette and collage energy are worthwhile, but cluttered notation, rough architectural definition, and incomplete symbolic integration limit success.
A city skyline that forms the shape of musical notes on a staff, created in a stylized graphic design aesthetic with clean architectural lines and dramatic twilight colors. - MiniMax Image-01
MiniMax Image-01 3 / 10 Rank 12 of 12: An attractive generic skyline, but unsuccessful at the task's defining visual interpretation. Missing both recognizable musical-note architecture and a staff is a critical prompt failure that outweighs its competent rendering.
Text in Images A technology magazine cover featuring the headline "Tech Innovations of 2025," clean modern design style.
A technology magazine cover featuring the headline "Tech Innovations of 2025," clean modern design style. - Midjourney V6.1
Midjourney V6.1 6 / 10 Ranked 9th of 13, this is a lively illustration with a weaker magazine identity. Its unconventional headline organization and crowded upper composition limit its effectiveness for this typography-focused prompt.
A technology magazine cover featuring the headline "Tech Innovations of 2025," clean modern design style. - MiniMax Image-01
MiniMax Image-01 3 / 10 Rank 12 of 12: failure to reproduce the primary headline is decisive in this typography-focused task. The book-like format and unreadable footer compound that fundamental error.
Ultra Hard Photorealistic aerial photograph clearly showing the edge of the Earth from space, capturing realistic curvature, atmosphere, and sunlight reflections
Photorealistic aerial photograph clearly showing the edge of the Earth from space, capturing realistic curvature, atmosphere, and sunlight reflections - Midjourney V6.1
Midjourney V6.1 4 / 10 Some curvature and sunlight are present, but the dominant cloud basin is poorly scaled and physically unconvincing. The lack of a clear space backdrop further weakens its response to the prompt.
Photorealistic aerial photograph clearly showing the edge of the Earth from space, capturing realistic curvature, atmosphere, and sunlight reflections - MiniMax Image-01
MiniMax Image-01 6 / 10 Ranks 10th of 12. Its dramatic presentation is effective, but exaggerated clouds and dominant artificial-looking flare make it one of the weaker photographic interpretations.

More comparisons