Black Forest Labs' compact, open-source image generation model with sub-second inference, optimized for production and near real-time applications with multi-reference support
Settled by community votes across 2 shared challenges, with an AI judge weighing in on each.
FLUX.2 [klein] 4B
22.3
arena score
#32 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Lucid Origin
23.4
arena score
#24 of 62 in Text-to-Image
Vote tally
Where the votes landed
FLUX.2 [klein] 4B
0%
win rate
Ties
0%
Lucid Origin
0%
win rate
Shared challenges
2
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
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.2 [klein] 4B
Lucid Origin
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent depiction of ornate engraved plate armor with realistic metal texture
- + Clear inclusion of small beads in the braided hair
- + Highly lifelike eyes and skin texture
- − Lighting is a bit flat despite the torches in the background
- − The hair braids look a bit symmetrical and unnatural
Lucid Origin
- + Beautiful cinematic lighting with strong torchlight highlights on the face
- + Superior depiction of the underlayer with knitted and fur textures
- + More natural and dynamic hair styling that fits the battle-worn theme
- − The beads are fewer and less distinct than requested
- − Lower contrast on the armor engravings compared to Model A
Verdict: Both models followed the prompt very well, but Lucid Origin captures a more cinematic and atmospheric 'paladin' feel with more dramatic lighting and complex textile textures. While FLUX.2 [klein] 4B has sharper armor engravings and more literal adherence to the 'beads' instruction, Lucid Origin's overall composition and lifelike intensity make it the stronger image.
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 [klein] 4B
Lucid Origin
AI Judge Analysis
FLUX.2 [klein] 4B
- + Excellent dynamic composition showing actual movement and play
- + Successfully included all animal types mentioned despite swapping the bunny for a second kitten
- + Beautifully rendered god rays and sharp fur textures
- − Missing the baby bunny completely, replacing it with a second kitten
- − The butterfly size and placement feel a bit artificial/overlayed
Lucid Origin
- + Successfully included a bunny/fox hybrid creature and a kitten closer to the prompt count
- + Great soft lighting and bokeh effect in the meadow
- + The kitten's facial expression is very endearing and fits the 'expressive eyes' prompt
- − The fox kit has bunny ears, which is a significant anatomical error
- − Animals are mostly sitting still rather than 'chasing and tumbling' as requested
Verdict: Both models struggled with the complex task of rendering four distinct baby animals in action. FLUX.2 [klein] 4B provided a much more energetic and high-quality image that captured the 'tumbling' and 'chasing' aspect better, although it missed the bunny. Lucid Origin combined the bunny and fox into a single creature with fox features and long ears, which resulted in a lower prompt adherence despite the cozy lighting.
Next steps
Explore each model
Leonardo AI's versatile image model producing artistic and high-quality visuals with improved prompt adherence, diversity, and definition