Fantasy Warrior
Vote
Text-to-Image
Portrait
19 models were given the same prompt, and the community voted blind on which outputs looked best. How it works
#1 — Lucid Origin
Prompt
“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.”
Challenge Rankings
| # | Model | Elo |
|---|---|---|
| 1 | Lucid Origin Leonardo AI | 1253 |
| 2 |
GPT Image 1.5
OpenAI
|
1250 |
| 3 | Stable Diffusion 3.5 Large Stability AI | 1236 |
| 4 |
Nano Banana Pro
Google
|
1222 |
| 5 | ImagineArt 1.5 (Preview) Vyro AI | 1210 |
| 6 |
GPT Image 1 Mini
OpenAI
|
1203 |
| 7 | FLUX.2 [dev] Turbo fal | 1193 |
| 8 |
Z-Image Turbo
Alibaba
|
1189 |
| 9 |
FLUX.2 [pro]
Black Forest Labs
|
1176 |
| 10 | HiDream I1 Fast HiDream AI | 1174 |
| 11 | FLUX.2 [dev] Flash fal | 1171 |
| 12 |
FLUX.2 [dev]
Black Forest Labs
|
1170 |
| 13 |
Grok Imagine Image
xAI
|
1159 |
| 14 |
Nano Banana 2
Google
|
1153 |
| 15 |
Grok Imagine Image Pro
xAI
|
1134 |
| 16 |
Reve Image 1.0
Reve AI
|
1116 |
| 17 |
Imagen 4.0 Fast Generate 001
Google
|
1110 |
| 18 |
Seedream 5.0 Lite
ByteDance
|
1093 |
| 19 |
Nano Banana
Google
|
1077 |
Lucid Origin leads with a 1253 Elo, though it is challenged by the more affordable GPT Image 1.5, which maintains a 1250 Elo at less than half the generation cost. Despite a 116-point Elo gap between the top and bottom of the leaderboard, budget-tier models like GPT Image 1 Mini ($0.005/img) frequently outperform premium alternatives costing over ten times as much.
Elo vs Cost
Elo vs Speed
9 without speed data omitted.
Competitors
19 models, ranked by Elo
1
2
3
Highlighted Battles
The most competitive head-to-head matchups, selected by closeness and vote count.
