Black Forest Labs' 12-billion parameter flow transformer for high-quality text-to-image generation, suitable for personal and commercial use with streaming support
Settled by community votes across 4 shared challenges, with an AI judge weighing in on each.
FLUX.1 [dev]
24.6
arena score
#16 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Reve Image 1.0
20.0
arena score
#42 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.1 [dev]
0.0%
win rate
Ties
0.0%
Reve Image 1.0
100.0%
win rate
0.0%
0.0% ties
100.0%
Shared challenges
4
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Geometric Composition
Text-to-Image“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”
FLUX.1 [dev]
Reve Image 1.0
AI Judge Analysis
FLUX.1 [dev]
- + Excellent handling of glass refraction and reflections
- + Photorealistic texture on the red book cover
- + Very high resolution and clear details
- − The cube geometry is slightly confused, appearing more like a frame or hollowed block in some areas
- − The scale of the sphere relative to the cube is a bit large
Reve Image 1.0
- + Strong adherence to the spatial requirements of the prompt
- + Accurate cube geometry
- + Effective use of soft window light and shadows on the wooden surface
- − The blue sphere looks a bit more like matte plastic than the glass-like quality of the other objects
- − Composition feels slightly more generic than the other model
Verdict: Both models followed the prompt instructions perfectly, including the placement of the sphere, book, and plant. FLUX.1 [dev] produced a more visually stunning image with superior glass physics and textures, while Reve Image 1.0 provided a more physically grounded composition with better logic regarding the cube's structure.
Fantasy Warrior
Text-to-Image“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
FLUX.1 [dev]
Reve Image 1.0
0% wins
0% ties
100% wins
AI Judge Analysis
FLUX.1 [dev]
- + Excellent high-resolution skin texture and lifelike eye detail
- + Very clean bokeh effect with light sparks
- + Captures a strong, symmetrical facial composition
- − Missing the specific request for beads in the hair
- − Character looks more like a fashion model than a battle-worn warrior
- − Plate armor feels somewhat generic and lacking the requested ornate engraving
Reve Image 1.0
- + Follows more prompt details including hair beads and ornate engraved armor
- + Effectively captures the 'battle-worn' aesthetic with visible dirt and scars
- + Strong atmospheric lighting from the torch accurately reflects on the metal
- − The facial features are slightly soft compared to the sharpness of the hair
- − The background torch has a slightly distracting, overexposed bloom
Verdict: While FLUX.1 [dev] produces a higher clarity, 'cleaner' image, it fails to incorporate specific prompt elements like the hair beads or the battle-worn grit. Reve Image 1.0 adheres much better to the prompt's storytelling requirements, delivering complex engravings and a realistic war-torn appearance.
Isometric Miniature Diorama Scenes
Text-to-Image“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”
FLUX.1 [dev]
Reve Image 1.0
AI Judge Analysis
FLUX.1 [dev]
- + Excellent high-fidelity textures with a soft subsurface scattering effect on the sushi.
- + Clean, professional composition with realistic depth of field.
- + Successfully included all requested elements like the diorama base and small flag.
- − Text rendering is inaccurate, displaying 'SUSH CATON' instead of 'SUSHI'.
- − The inclusion of random vertical flowers wasn't explicitly requested and slightly clutters the top-center area.
Reve Image 1.0
- + Perfect text rendering for 'JAPAN' and 'SUSHI'.
- + Strong adherence to the 45-degree isometric perspective and diorama style.
- + Highly vibrant and clean 3D cartoon aesthetic.
- − The sushi toppings look very plasticky and lack the 'refined textures' or 'realistic PBR' look requested.
- − The layout of the sushi pieces on the plate appears slightly cramped and geometric.
Verdict: FLUX.1 [dev] produced a much more sophisticated image with beautiful lighting and realistic materials that match the 'miniature' look, though it failed to spell the text correctly. Reve Image 1.0 followed the text and composition instructions perfectly but resulted in a flatter, more basic 3D model look that lacks the high-end quality of the sushi in Image A. FLUX.1 [dev] is the likely winner for its superior visual fidelity and artistic execution of the 3D scene.
Apollo 11: Journey to Tranquility
Text-to-Image“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”
FLUX.1 [dev]
Reve Image 1.0
AI Judge Analysis
FLUX.1 [dev]
- + Elegant layout with a unified diagrammatic approach.
- + Strong adherence to the NASA-inspired color palette and flat-vector style.
- + Beautifully rendered central rocket and atmospheric elements.
- − Text is largely illegible gibberish throughout the infographic.
- − Logical flow of steps is circular and confusing, failing to clearly represent the sequential journey requested.
Reve Image 1.0
- + Excellent adherence to the sequential 6-step structure requested.
- + Text is much more legible and accurate, correctly naming crew members and mission phases.
- + Clean, modern iconography that clearly distinguishes between Earth, Moon, and Landing modules.
- − Includes some minor spelling errors in major labels (e.g., 'Dessent', 'Lunnr').
- − The addition of green and blue in the Earth icon deviates slightly from the requested 'muted' NASA palette.
Verdict: Reve Image 1.0 is the clear winner because it actually functions as an infographic, providing a clear, numbered 1-6 sequence that matches the stages requested in the prompt. While FLUX.1 [dev] has a more sophisticated artistic style, its content is nonsensical and fails to communicate the requested mission steps logically.
Next steps
Explore each model
Reve AI's text-to-image generation model with strong aesthetic quality, accurate text rendering, and detailed instruction following capabilities