Fast distilled version of Black Forest Labs' FLUX.2 [dev] optimized for speed and cost efficiency.
Settled by community votes across 5 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev] Flash
26.8
arena score
#5 of 44 in Text-to-Image
Skill signature
Not enough comparable category data
The chart appears once both models have ratings across at least three shared arena categories.
FLUX.2 [flex]
25.2
arena score
#13 of 44 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [dev] Flash
83.3%
win rate
Ties
0.0%
FLUX.2 [flex]
16.7%
win rate
83.3%
0.0% ties
16.7%
Shared challenges
5
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.2 [dev] Flash
FLUX.2 [flex]
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [dev] Flash
- + Excellent photographic realism with natural textures and dust on the glass
- + Highly accurate lighting and reflections that react to the surrounding environment
- + Perfect adherence to all spatial relationships in the prompt
- − The glass cube is slightly weathered/dusty, which might be less 'clean' than some users prefer
FLUX.2 [flex]
- + Clean, minimalist aesthetic
- + Follows all prompt instructions regarding object placement
- − Lighting and reflections look artificial and plastic-like
- − The blue sphere appears matte and lacks the depth of the glass sphere in the first image
- − Lower detail level on the book and table textures
Verdict: FLUX.2 [dev] Flash produces a significantly more realistic image with convincing glass reflections, wood grain, and atmospheric lighting. While both models followed the complex spatial prompt perfectly, FLUX.2 [flex] has a more CG/rendered look that lacks the fine details and photographic quality of the Flash model.
Candid Street Photography
Text-to-Image“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”
FLUX.2 [dev] Flash
FLUX.2 [flex]
AI Judge Analysis
FLUX.2 [dev] Flash
- + Excellent adherence to the 'motion blur from passing cars' prompt.
- + Highly realistic skin texture and elderly features.
- + Detailed bicycle components and believable wet pavement reflections.
- − The bike's kickstand and tools on the ground are slightly distorted.
- − The composition is a bit centered despite the request for imperfect framing.
FLUX.2 [flex]
- + Strong 'candid' feel with more dynamic 'imperfect' framing.
- + Beautiful bokeh and lighting in the background.
- + Good natural skin texture on the man's hands and face.
- − The motion blur on the cars is much less pronounced than requested.
- − The bicycle's anatomy is slightly simplified and less detailed than Image A.
Verdict: FLUX.2 [dev] Flash captures the specific prompt requirements much better, particularly the motion blur of the passing cars and the detailed mechanics of the bicycle. While FLUX.2 [flex] offers a more artistically framed candid shot, it fails to deliver the requested level of motion blur and the bike's structure is less convincing.
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.2 [dev] Flash
FLUX.2 [flex]
0% wins
0% ties
100% wins
AI Judge Analysis
FLUX.2 [dev] Flash
- + Perfect text rendering and placement next to the flag
- + High-quality realistic PBR textures on the wood and fish
- + Excellent 45-degree isometric perspective
- − The sushi design is slightly unusual with fish draped over a roll-style base
FLUX.2 [flex]
- + Clean aesthetic with a professional-looking rounded diorama base
- + Variety of sushi types included (nigiri and maki)
- + Accurate flag icon rendering
- − The text is not 'top-center' as requested, but rather centered over the whole image
- − The fish textures appear more like plastic/clay than realistic PBR materials
Verdict: FLUX.2 [dev] Flash adhered better to the layout instructions, placing the text at the top-center and capturing a more realistic 'PBR' material look on the wood and salmon. FLUX.2 [flex] produced a very clean image but the text placement crowded the subject and the materials lacked the refined texture promised in the prompt.
Adorable Baby Animals in Sunny Meadow
Text-to-Image“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”
FLUX.2 [dev] Flash
FLUX.2 [flex]
AI Judge Analysis
FLUX.2 [dev] Flash
- + Excellent depiction of dew sparkles and golden hour lighting.
- + Highly detailed fur texture on all animals.
- + Expressive and biologically distinct eyes for each animal.
- − Included an extra fifth animal (a hybrid cat/rabbit) in the foreground.
- − The animals are somewhat static and crowded together.
FLUX.2 [flex]
- + Successfully captured the 'tumbling' and 'chasing' action requested in the prompt.
- + Correct count of animals as specified (puppy, kitten, bunny, fox).
- + Great use of depth perception and environmental lighting/god rays.
- − The fox's front leg has a slightly awkward anatomical join.
- − The kitten's facial structure is a bit less realistic compared to the other animals.
Verdict: Both models followed the aesthetic requirements of the prompt well, but FLUX.2 [flex] is the superior image because it accurately adhered to the animal count and better captured the requested movement. FLUX.2 [dev] Flash produced higher individual detail on the fur and dew, but it hallucinated a fifth animal that appears to be a kitten-rabbit hybrid.
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.2 [dev] Flash
FLUX.2 [flex]
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [dev] Flash
- + Includes all six requested steps and extra details like the crew and landing site.
- + Adheres strictly to the requested color palette (navy, white, muted red, gray).
- + Images of the lunar module and Earth are highly detailed or realistic.
FLUX.2 [flex]
- + Closer adherence to the requested 'flat-vector style' with clean, minimalist iconography.
- + Excellent text rendering and typography that feels like a professional infographic.
- + Balanced, vertical layout that clearly distinguishes the mission phases.
- − Misses the final 'Landing' step requested in the prompt.
- − The 'Lunar Orbit' and 'Descent' steps are slightly out of sequential order in the layout.
Verdict: FLUX.2 [dev] Flash followed the content instructions more accurately by including all six steps, whereas FLUX.2 [flex] missed the final landing step. However, FLUX.2 [flex] captured the requested 'flat-vector style' and professional infographic aesthetic much better than FLUX.2 [dev] Flash, which struggled with text legibility and had redundant icons.
Next steps
Explore each model
Black Forest Labs' precision image generation model with maximum control, reliable text rendering, and complete creative control supporting up to 4MP output