HiDream AI's 17B parameter text-to-image model using sparse diffusion transformer with mixture of experts, achieving state-of-the-art image generation quality with strong prompt following
Settled by community votes across 2 shared challenges, with an AI judge weighing in on each.
HiDream I1 Full
13.7
arena score
#60 of 62 in Text-to-Image
Skill signature
· Text-to-Image
Lucid Origin
23.4
arena score
#26 of 62 in Text-to-Image
Vote tally
Where the votes landed
HiDream I1 Full
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.”
HiDream I1 Full
Lucid Origin
AI Judge Analysis
HiDream I1 Full
- + Excellent adherence to the 'beads in hair' prompt element.
- + Strong, vivid torchlight reflections on the plate armor.
- + Sharp, detailed skin textures and realistic battle scars.
- − The lighting feels slightly over-processed and overly saturated.
- − The symmetry of the scars on the forehead looks a bit unnatural.
Lucid Origin
- + Beautifully soft and realistic skin texture with subtle dirt and freckling.
- + Highly sophisticated engraving details on the armor collar.
- + Naturalistic bokeh and a very moody, cinematic color palette.
- − The hair beads are fewer and less distinct than in Model A.
- − Lighting is more muted and lacks the 'warm torchlight' intensity requested.
Verdict: HiDream I1 Full delivers a more vibrant and literal interpretation of the prompt, particularly with the lighting and hair accessories. Lucid Origin, however, offers superior visual quality with much finer armor engravings and more believable skin textures. Lucid Origin is the winner for its professional cinematic composition and subtle, lifelike details.
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.”
HiDream I1 Full
Lucid Origin
AI Judge Analysis
HiDream I1 Full
- + Excellent depiction of golden sunrise lighting and bokeh
- + Vibrant colors that enhance the joyful vibe
- + Clear and distinct character rendering for the puppy and fox
- − Failed to include the baby bunny
- − Included two kittens instead of one
- − The style is more illustrative/3D render than hyper-photorealistic
Lucid Origin
- + Better adherence to the photorealistic request with realistic fur textures
- + Beautiful god rays and atmospheric lighting
- + Includes puppy, kitten, and a hybrid-looking fox/bunny creature
- − Anatomical merging where the fox and bunny appear to be one creature
- − Missing clear, separate animals as requested in the list
- − The puppy has a strange blue collar/tag not requested in the prompt
Verdict: Both models struggled to correctly render all four distinct animals and the specific 'tumbling' action. HiDream I1 Full produced a cleaner, more vibrant image but failed significantly on the animal count by adding an extra kitten and omitting the bunny entirely. Lucid Origin achieved a more realistic photographic texture and better lighting effects but suffered from severe anatomical merging between the fox and bunny, making the composition confusing.
Next steps
Explore each model
Leonardo AI's versatile image model producing artistic and high-quality visuals with improved prompt adherence, diversity, and definition