whatmodel.sh / image / ERNIE-Image
ERNIE-Image
↗ share
+ contribute
ERNIE-Image is an open-weights image model from Baidu, released April 2026. Its published size is 8B parameters. Licence: apache-2.0.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of ERNIE-Image, out of 197 with a score.
| # | model | score | where |
|---|---|---|---|
| 47 | ERNIE-Image-Turbo | 61±3 | api $0.010/image +local |
| 48 |  Emu3.5-Image | 60±5 | local |
| 49 | ERNIE-Image | 60±2 | api $0.030/image +local |
| 50 |  Kling Image O1 | 60±4 | api $0.028/image |
| 51 |  Krea 2 Medium | 60±3 | api $0.030/image |
$ what it's good at
text to image▂▅▅▃▄▄█▃▁▂▁▁ #29 of 126 · 84% of its score · 6 tests
Beats Wan 2.7 Image Pro, Cosmos3-Super-Text2Image, Nano Banana (Gemini 2.5 Flash Image) here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| QC-T2I-Bench (English, HCQ total) | 89.4% ✎ | ▄····▄█▄▄█▄█ beats 9/10 | 24% |
| LongText-Bench (EN) lab | 96.8% ✎ | ▃·····▅██▅▃▃ beats 11/12 | 16% |
| LongText-Bench (CN) lab | 95.9% ✎ | ▃·······████ beats 9/12 | 13% |
| GenEval lab | 88.6% ✎ | ▇▃▅▇▁▄▅▃█▃▃▅ beats 37/39 | 12% |
| OneIG-Bench (CN) lab | 52.1% ✎ | ▃·▃█▃·▃··▃·▃ beats 6/8 | 10% |
| OneIG-Bench (EN) lab | 55.4% ✎ | ▃······▃▅█▅▃ beats 9/9 | 10% |
other tests1 not in a task · 13% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Rapidata Benchmark.ai image benchmark (overall Elo) | 896.9 ✎ | ▁▁▃▄▂█▂▁▁▂▁▁ beats 3/34 | 13% |
$ where to run it
Through an API
api · fal.ai · $0.030/image · fal.ai ↗ · price sourceUSD for one 1-megapixel output: fal bills this endpoint $0.03 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. API model: fal-ai/ernie-image. 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
- Run it as published · needs ~17.1 GB · from github.com/leejet
sd-cli --diffusion-model models/ernie-image-UD-Q4_K_M.gguf --vae models/flux2_ae.safetensors --llm models/ministral-3-3b.safetensors -p "a lovely cat" --cfg-scale 5.0 -v --offload-to-cpu --diffusion-fa
Official weights and documentation: huggingface.co/baidu ↗
$ how the score was worked out · ERNIE-Image model repository… 60%, QC-T2I-Bench: Scalable Questi… 24%, Rapidata/text-to-image-human-… 13%
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
| source | results | share of the score |
|---|---|---|
 ERNIE-Image model repository evaluation tables · lab-reported | 5 | 60% |
 QC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing) | 1 | 24% |
| Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings | 1 | 13% |
| prior · pull toward the middle | 2% | |
| weighted average | = 60.1 |
$ improve this page
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