Black Forest Labs' open-weights image generation model with frontier performance, available for non-commercial local deployment
Settled by community votes across 3 shared challenges, with an AI judge weighing in on each.
FLUX.2 [dev]
24.5
arena score
#17 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 [max]
25.9
arena score
#11 of 44 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [dev]
66.7%
win rate
Ties
0.0%
FLUX.2 [max]
33.3%
win rate
66.7%
0.0% ties
33.3%
Shared challenges
3
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]
FLUX.2 [max]
100% wins
0% ties
0% wins
AI Judge Analysis
FLUX.2 [dev]
- + Perfect adherence to the prompt's spatial instructions.
- + Excellent glass refraction and lighting consistency.
- + Warm, natural photographic aesthetic.
- − The blue sphere appears slightly levitating rather than resting on the bottom.
FLUX.2 [max]
- + High-fidelity textures, specifically on the book cover and wooden table.
- + Sharp, clean geometry for the glass cube.
- + Realistic light streaks on the table surface.
- − The sphere is not truly 'inside' the cube, appearing to float through or in front of the glass pane.
- − The glass cube lacks a bottom, making its structure physically confusing.
Verdict: FLUX.2 [dev] followed the spatial instructions perfectly, accurately placing the plant behind the glass and the sphere inside it. While FLUX.2 [max] has slightly more crisp textures, it failed the core logic of the prompt by rendering the blue sphere as if it were passing through the front glass panel and omitting the bottom of the cube.
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]
FLUX.2 [max]
0% wins
0% ties
100% wins
AI Judge Analysis
FLUX.2 [dev]
- + Excellent representation of motion blur from passing cars.
- + Highly realistic skin texture and facial details.
- + Stronger 'candid' feel with messy foreground elements and imperfect framing.
- − The structural integrity of the bike is poor, with mismatched parts and confusing geometry.
- − The man's hands melt into the bike's handlebars and wires.
FLUX.2 [max]
- + The bicycle is significantly more coherent and realistic in its construction.
- + The composition is clean and clearly depicts the act of 'repairing' with tools on the ground.
- + Good use of wet pavement reflections and shallow depth of field.
- − Missed the 'motion blur from passing cars' instruction; the background car is sharp.
- − The framing feels a bit too staged and centered compared to the 'imperfect' request.
Verdict: FLUX.2 [dev] followed the technical prompt instructions better, specifically the inclusion of motion blur and the 'imperfect framing' of a candid street shot, though it struggled with the logical anatomy of the bicycle. FLUX.2 [max] produced a much more structurally sound bicycle and a very high-quality subject, but it ignored the motion blur requirement and felt more like a posed portrait than a candid street photo. FLUX.2 [dev] is preferred for closer adherence to the specific atmospheric and cinematic requests.
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]
FLUX.2 [max]
AI Judge Analysis
FLUX.2 [dev]
- + Expertly rendered 'god rays' and backlighting that creates a warm, atmospheric glow.
- + Individual fur strands and whiskers are exceptionally sharp and detailed.
- + Excellent expressions on the animals that feel emotive and 'wholesome'.
- − Included two rabbits instead of the one requested in the prompt.
- − The animals are sitting relatively still rather than 'playfully chasing' or 'tumbling'.
FLUX.2 [max]
- + Perfectly captures the 'playfully chasing' and 'tumbling' movement described in the prompt.
- + Includes exactly one of each animal requested (puppy, kitten, bunny, fox).
- + Dynamic composition with butterflies scattered throughout the scene.
- − The fox's front paws/legs look slightly anatomically awkward in the mid-air pose.
- − The lighting is slightly flatter and less 'magical' compared to the god rays in the other image.
Verdict: Both models produced high-quality, adorable results, but FLUX.2 [max] is the winner for its superior prompt adherence regarding both the animal count and the active movement of 'chasing and tumbling.' While FLUX.2 [dev] has slightly more impressive cinematic lighting and fur textures, it failed the specific count by adding an extra rabbit and depicted a static scene rather than an active one.
Next steps
Explore each model
Black Forest Labs' flagship image generation model delivering state-of-the-art quality with exceptional realism, precision, and consistency for both text-to-image and advanced image editing