Black Forest Labs' distilled 9 billion parameter image generation model with sub-second inference and multi-reference support
Settled by community votes across 2 shared challenges, with an AI judge weighing in on each.
FLUX.2 [klein] 9B
21.3
arena score
#7 of 23 in Image Editing
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 [klein] 9B
0.0%
win rate
Ties
100.0%
FLUX.2 [max]
0.0%
win rate
0.0%
100.0% ties
0.0%
Shared challenges
2
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
Magic Burger Explosion: Fiery Photorealism Challenge
Text-to-Image“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”
FLUX.2 [klein] 9B
FLUX.2 [max]
0% wins
100% ties
0% wins
AI Judge Analysis
FLUX.2 [klein] 9B
- + Excellent typography with a glowing fire texture in the main title.
- + The starburst design for the price is dynamic and fits the fiery theme well.
- + Great use of motion blur and embers to create a sense of action.
- − The burger is less 'exploded' than the competitor, retaining a mostly stacked shape.
- − The bottom half of the burger looks slightly disconnected from the top half's lighting.
FLUX.2 [max]
- + Superior 'exploded' effect with sauce swirls and distinctly suspended layers.
- + Highly detailed food textures, particularly the sesame seed bun and the tomato slices.
- + The 'MAGIC BURGER' text matches the fiery prompt perfectly with actual flame effects.
- − The price starburst looks like a flat graphic sticker rather than an integrated part of the 3D scene.
- − The secondary text 'LIMITED TIME ONLY' is smaller and less impactful than in the other version.
Verdict: FLUX.2 [max] is the winner for its superior interpretation of the 'exploded' burger, showing more sauce detail and clearly suspended layers. While FLUX.2 [klein] 9B has a better starburst design for the price, the overall composition and food photography quality in the [max] version feel more premium and better aligned with the 'action' prompt.
Pose & Character Mashup
EditingEdit instruction
“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”
Source
FLUX.2 [klein] 9B
FLUX.2 [max]
AI Judge Analysis
FLUX.2 [klein] 9B
- + Excellent adherence to the complex leg-crossing pose from Image 1.
- + Accurately replicates the character details including the scarf, sunglasses, and hairstyle.
- + Faithfully matches the vibrant yellow studio lighting and background colors.
- − The right hand is rendered as a distorted fist without clear fingers.
- − The transition between the neck and the scarf is slightly unnatural due to the head tilt.
FLUX.2 [max]
- + High resolution and realistic skin textures.
- + Captures the character's facial likeness and accessories effectively.
- + Smooth integration of the scarf with the sweatshirt.
- − Fails significantly on the pose, choosing a standard squat instead of the dynamic leg-cross in Image 1.
- − The character is wearing shoes, whereas Image 1 and the prompt implied bare feet or exact pose replication.
- − Lighting is much darker and moodier than the reference Image 1.
Verdict: FLUX.2 [klein] 9B is the clear winner as it successfully followed the difficult instructions to merge the character from Image 2 with the specific dynamic pose from Image 1. FLUX.2 [max] failed to replicate the core pose requirement, providing a generic crouching position instead of the unique crossed-leg balance seen in the reference.
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