whatmodel.sh / image / Lucid Origin

Lucid Origin

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Lucid Origin is a closed-weights image model from Leonardo.Ai, released August 2025.

Model information sources

Release date ↗

48.5±2.5#84 of 144 image modelsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the LMArena text-to-image comparison set only.

$ how it compares

The image models ranked either side of Lucid Origin, out of 197 with a score.

#modelscorewhereRAMreleased
103Step1X-Edit v1.2 Preview StepFun50±5comparison only2025-09
104Runway Gen-4 Image Runway50±3api $0.050/image
105Lucid Origin Leonardo.Ai49±3api $0.017/image2025-08
106Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M) CompVis48±15local~7.5GB2022-04
107Kandinsky 3 AI Forever48±11local~32GB2023-11

see all image models · find the ones that fit your machine

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▁▁ #73 of 126 * · 97% of its score · 1 test

Trails Kandinsky 3 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena text-to-image1013.0 ✎▂▂▃▄▇█▄▂▄▂·▂ beats 7/75avg 1027▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%typical

$ where to run it

Through an API

api · Replicate · $0.017/image · replicate.com ↗ · price sourceUSD per output image, Standard generation mode, on Replicate's official model leonardoai/lucid-origin (billing table: Standard $0.0167 per output image, Ultra $0.0765 per output image; generation_mode defaults to standard; no hardware-time charge). Product: Replicate model API (Leonardo.Ai's Lucid Origin). API model: leonardoai/lucid-origin. Settings: generation_mode=standard, default aspect ratio 16:9, one image. Price basis: published per-output-image list rate. Leonardo's own API bills from a USD balance but its per-image rates are only in the logged-in pricing calculator (leonardo.ai pricing pages return a Cloudflare challenge). Currency: USD. Not a Leonardo.Ai direct tariff. Replicate official model page, observed 2026-09-26.

$ how the score was worked out · LMArena leaderboard dataset 97%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 97%CC BY 4.0
prior · pull toward the middle▇ 3%
weighted average= 48.5

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json