whatmodel.sh / image / ERNIE-Image-Turbo

ERNIE-Image-Turbo

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

ERNIE-Image-Turbo is an open-weights image model from Baidu, released April 2026. Its published size is 8B parameters. Licence: apache-2.0.

60.5±3.0#40 of 144 image modelsfrom 5 benchmark results across 1 source

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

$ how it compares

The image models ranked either side of ERNIE-Image-Turbo, out of 197 with a score.

#modelscorewhereRAMreleased
45Seedream 4.0 ByteDance Seed61±1api $0.040/image2025-09
46Recraft V4.1 Pro Recraft61±3api $0.21/image2026-05
47ERNIE-Image-Turbo Baidu61±3api $0.010/image +local~17GB2026-04
48Emu3.5-Image BAAI60±5local~85GB2025-10
49ERNIE-Image Baidu60±2api $0.030/image +local~17GB2026-04

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

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▁▁ #32 of 126 · 96% of its score · 5 tests

Beats Wan 2.7 Image Pro, Wan 2.7 Image, Imagen 4 Ultra here, though they rank higher overall. Trails ERNIE-Image here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LongText-Bench (EN) lab96.0% ✎▃·····▅██▅▃▃ beats 10/12very easy · avg 90%▇▇▇▇▇▇▇▇▇▇ 25%maxed out · small run
LongText-Bench (CN) lab96.8% ✎▃·······████ beats 10/12very easy · avg 91%▇▇▇▇▇▇▇▇ 20%maxed out · small run
GenEval lab86.7% ✎▇▃▅▇▁▄▅▃█▃▃▅ beats 34/39easy · avg 78%▇▇▇▇▇▇▇ 19%small run
OneIG-Bench (CN) lab50.6% ✎▃·▃█▃·▃··▃·▃ beats 2/8medium · avg 37%▇▇▇▇▇▇ 16%at its level · small run
OneIG-Bench (EN) lab53.4% ✎▃······▃▅█▅▃ beats 4/9medium · avg 39%▇▇▇▇▇▇ 16%at its level · small run

$ where to run it

Through an API

api · fal.ai · $0.010/image · fal.ai ↗ · price sourceUSD for one 1-megapixel output: fal bills this endpoint $0.01 per output megapixel (price = rate × 1 MP; fal's rounding for 1024×1024 ≈ 1.05 MP is not stated; larger outputs cost proportionally more). Product: fal.ai serverless text-to-image (Turbo, 8 steps default). API model: fal-ai/ernie-image/turbo. Settings: 1 MP output, num_images=1. Price basis: published per-megapixel list rate × 1 MP. Currency: USD. Not a Baidu direct tariff. fal.ai official model page, observed 2026-09-25.

Other ways to run it

version

  1. Run it as published · needs ~17.1 GB · from github.com/leejet
    sd-cli --diffusion-model models/ernie-image-turbo-UD-Q4_K_M.gguf --vae models/flux2_ae.safetensors --llm models/ministral-3-3b.safetensors -p "a lovely cat" --cfg-scale 1.0 --steps 8 -v --offload-to-cpu --diffusion-fa

Official weights and documentation: huggingface.co/baidu ↗

$ how the score was worked out · ERNIE-Image model repository… 96%

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
ERNIE-Image model repository evaluation tables · lab-reported5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%Apache-2.0
prior · pull toward the middle▇ 4%
weighted average= 60.5

$ 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