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
#25 of 62 in Text-to-Image
Wan 2.5 (Preview)
#27 of 62 in Text-to-Image
Where the votes landed
Lucid Origin
0%
win rate
Ties
0%
Wan 2.5 (Preview)
0%
win rate
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.”
AI Judge Analysis
Lucid Origin
- + Excellent skin texture with realistic pores and fine hair details.
- + Beautifully intricate engraving on the plate armor that looks physically etched.
- + Strong adherence to the 'beads in braids' request with natural-looking wooden beads.
- − The lighting feels more like a studio glow than actual warm torchlight.
- − The scarring and dirt are very subtle, leaning more toward 'clean' than 'battle-worn'.
Wan 2.5 (Preview)
- + Perfectly captures the 'warm torchlight' atmosphere with high-contrast shadows and orange highlights.
- + The textures of the cloth, chainmail, and leather straps are extremely detailed and tactile.
- + Successfully portrays a gritty, battle-worn look with visible wounds and dirt.
- − The beads in the hair look a bit like shiny metallic pins rather than integrated beads.
- − The shoulder plate engraving, while good, lacks the depth and definition found in the other model.
Verdict: Lucid Origin produces a very high-quality portrait with superior skin and armor engraving details, but it feels slightly too polished for the prompt. Wan 2.5 (Preview) captures the requested atmosphere much better, using dramatic torchlight and more realistic grit/dirt to convey the 'battle-worn' theme. Wan 2.5 is preferred for its superior lighting and texture variety across armor, leather, and cloth.
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.”
AI Judge Analysis
Lucid Origin
- + Excellent fur texture rendering and lighting
- + Beautifully integrated god rays and soft focus
- + High aesthetic appeal with a cohesive painterly style
- − Failed to include the requested baby bunny
- − The 'fox' appears to be a hybrid of a kitten and a fox
- − Less dynamic movement compared to the prompt requirements
Wan 2.5 (Preview)
- + Successfully included all four requested animals (dog, cat, bunny, fox)
- + Excellent depiction of dynamic movement and 'playfully chasing'
- + Clear droplets of dew and sharp butterflies
- − The fox kit has unsettling, overly saturated glowing blue eyes
- − The dew drops are floating in the air like glass spheres rather than resting on surfaces
- − The kitten's tail is abnormally long and stiff
Verdict: Wan 2.5 (Preview) followed the complex prompt much more accurately by including all four distinct animals and capturing the sense of movement, whereas Lucid Origin missed the bunny entirely. Although Lucid Origin has a more realistic and soft lighting quality, Wan 2.5 (Preview) is the winner for its superior prompt adherence and joyful energy, despite the strange eye color for the fox.
Explore each model
Alibaba's text-to-image and image-to-image generation model from the Wan AI suite, offering high-quality visual generation capabilities