Leonardo AI's versatile image model producing artistic and high-quality visuals with improved prompt adherence, diversity, and definition
Settled by community votes across 2 shared challenges, with an AI judge weighing in on each.
Lucid Origin
23.4
arena score
#26 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Stable Diffusion 3.5 Medium
16.8
arena score
#56 of 62 in Text-to-Image
Vote tally
Where the votes landed
Lucid Origin
0%
win rate
Ties
0%
Stable Diffusion 3.5 Medium
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.”
Lucid Origin
Stable Diffusion 3.5 Medium
AI Judge Analysis
Lucid Origin
- + Excellent adherence to the 'beads in braids' prompt with clear, realistic wooden beads.
- + Highly detailed engraving on the plate armor that looks coherent and metallic.
- + Very lifelike skin texture and eyes that convey a weary, battle-worn expression.
- − The 'scars' look more like dirt smudges than actual healed scar tissue.
- − Missing the specific 'leather straps' requested in the prompt.
Stable Diffusion 3.5 Medium
- + Dynamic warm lighting that looks like direct fire or torchlight reflecting off the skin and metal.
- + Intricate braid structure that matches the 'battle-worn' aesthetic well.
- + Good contrast and saturation making for a punchy, cinematic image.
- − Completely failed to include the requested beads in the braids.
- − Visible artifacts on the right shoulder pauldron where the texture looks blurry and smudged.
- − The engraving on the chest plate looks flat and lacks the depth seen in the competing model.
Verdict: Lucid Origin is the winner due to its superior technical execution of fine details, specifically the engraving on the armor and the presence of beads in the hair braids as requested. While Stable Diffusion 3.5 Medium has more dramatic lighting, it failed on key prompt elements and contains noticeable blurring on the armor pieces.
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.”
Lucid Origin
Stable Diffusion 3.5 Medium
AI Judge Analysis
Lucid Origin
- + Excellent soft fur textures and realistic anatomy for all animals.
- + Beautiful lighting with subtle god rays and a consistent atmospheric glow.
- + High level of detail in the butterflies and foreground wildflowers.
- − Failed to include all four requested animals, missing the baby bunny or distinctly merging its features.
- − The composition feels slightly static despite the 'chasing' prompt.
Stable Diffusion 3.5 Medium
- + Bright, vibrant colors that enhance the joyful and wholesome vibe.
- + Good variety in flower types and clear butterfly wings.
- − Failed to include all four animals, featuring only three.
- − Anatomical inconsistencies, specifically the kitten having large pointed ears resembling a fennec fox or rabbit.
- − The fur texture appears more digital and painterly rather than hyper-photorealistic.
Verdict: Both models failed to include the full count of four distinct animals (golden retriever, kitten, bunny, and fox), with Lucid Origin providing three and Stable Diffusion 3.5 Medium providing three. Lucid Origin is the clear winner as it achieves a much higher level of photorealism and consistent anatomy, whereas Stable Diffusion 3.5 Medium has a more plastic look and confusing ear anatomy on the central animal.
Next steps
Explore each model
Stability AI's 2.5-billion parameter Multimodal Diffusion Transformer with improvements (MMDiT-X) text-to-image model optimized for consumer hardware, featuring improved image quality, typography, and complex prompt understanding