Black Forest Labs' 12 billion parameter distilled image generation model optimized for speed, capable of generating high-quality images in just 4 inference steps
Settled by community votes across 4 shared challenges, with an AI judge weighing in on each.
FLUX.1 [schnell]
18.7
arena score
#48 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 [schnell]
0%
win rate
Ties
0%
Reve Image 1.0
0%
win rate
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 [schnell]
Reve Image 1.0
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent clarity and depth in the glass cube reflections.
- + Vibrant colors and high-resolution details on the plant leaves.
- − Included an extra blue sphere on top of the red book.
- − The sphere inside looks like it is floating or perfectly centered in a way that feels slightly unnatural.
Reve Image 1.0
- + Perfect adherence to all prompt elements with no extra objects.
- + Realistic lighting and shadows that correctly interact with the window light.
- + Accurately depicts the plant being partially visible through the glass.
- − The glass cube has a slight greenish/blue tint compared to the clear glass in Model A.
- − The background plant is slightly more blurred.
Verdict: Reve Image 1.0 is the clear winner as it followed every instruction in the prompt perfectly, whereas FLUX.1 [schnell] hallucinated an additional blue sphere on top of the book. Reve Image 1.0 also achieved a very natural-looking light and shadow interplay on the wooden surface.
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 [schnell]
Reve Image 1.0
AI Judge Analysis
FLUX.1 [schnell]
- + Intense, high-quality facial details and lifelike eye texture
- + Excellent rendering of lighting on the skin and hair
- − The armor is cropped too heavily, making the engravings hard to see
- − The hair beads requested in the prompt are largely missing or indistinct
Reve Image 1.0
- + Perfect adherence to the 'braided with small beads' and 'ornate engraved plate armor' prompts
- + Excellent environmental atmosphere with bokeh sparks and visible torchlight reflections
- + Accurate depiction of dirt and faint scars on the face
- − The facial features are slightly softer and less 'battle-worn' than the character in image A
- − The skin texture is a bit smooth compared to the hyper-detailed look of model A
Verdict: While FLUX.1 [schnell] creates a more striking and detailed face, Reve Image 1.0 is the superior choice for prompt adherence, accurately depicting every specific detail from the beads in the hair to the elaborate engravings on the armor. Reve Image 1.0 also captures the requested 'bokeh sparks' and environmental lighting much better than FLUX.1 [schnell].
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 [schnell]
Reve Image 1.0
AI Judge Analysis
FLUX.1 [schnell]
- + Excellent high-clarity 3D rendering with realistic material textures
- + Clean and professional minimalist composition
- + Perfectly maintains the requested isometric angle and diorama base
- − Failed to include the word 'SUSHI' in the text
- − The white text lacks contrast against the light blue background
Reve Image 1.0
- + Strictly followed all text requirements including 'JAPAN' and 'SUSHI'
- + Playful 3D cartoon aesthetic with charming garnish details
- + Good color contrast between text and background
- − The 'JAPAN' text is slightly off-center to the left
- − Textures are very simple and plastic-like, lacking the 'refined' and 'PBR' quality requested
Verdict: Reve Image 1.0 followed the complex text instructions much better by including both required words, whereas FLUX.1 [schnell] missed 'SUSHI' entirely. However, FLUX.1 [schnell] produced a significantly higher quality render with sophisticated materials and lighting that aligns better with the 'refined' and 'high-clarity' aspects of the prompt.
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 [schnell]
Reve Image 1.0
AI Judge Analysis
FLUX.1 [schnell]
- + Clean vector aesthetic with sophisticated usage of space.
- + Followed the color palette instructions very well.
- + Includes a central diagram that implies trajectory.
- − Text is largely gibberish and poorly rendered.
- − Iconography does not clearly match the specific steps requested in the prompt.
- − The layout is somewhat confusing as an instructional infographic.
Reve Image 1.0
- + Successfully followed the 6-step layout requested in the prompt.
- + Text rendering is legible, despite spelling errors.
- + Iconography is consistent and directly relates to the specific mission phases.
- − Failed to stop at step 6, adding an extra 'Tranquility Landing' step.
- − Visual style is a bit more generic compared to the first model.
- − Some spelling errors like 'Lunnr' and 'Dessent'.
Verdict: Reve Image 1.0 is the winner as it much more closely adheres to the logical structure and specific steps outlined in the prompt. While FLUX.1 [schnell] has a more professional artistic finish, its inability to render the requested steps and legible text makes it less effective as an infographic.
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