local/hidream-i1-full-17b Benchmark — 43/100 Overall, 192 Prompts, Every Image Shown

ImageBench V1 —

192 evaluations across 6 categories

Benchmark V1 verdicts are produced by VLM judges and can contain mistakes. Treat PASS/FAIL labels as machine-assisted assessments, and inspect the images yourself. Learn more about the methodology.

Generation Details

Source-backed model context, size, cost, and request settings for this run.

MakerHiDream

FamilyHiDream

Model size17B17B params

Costself-hostedfree

Latency91.3s median

Run targetlocal/hidream-i1-full-17b

Effective requestmodel: hidream-i1-full-17b · size: 1024x1024 · seed: 42

SourcesModel cardWeights & checkpoint

All 192 generations

Every challenge, grouped by category and subcategory. Solid-bordered tiles with a check passed the VLM judge; dashed tiles with a cross failed. Images are placeholders until generated.

Text Rendering

29%

Typography Style33%

Writing accuracy25%

Spatial Reasoning

34%

Attributes Binding33%

Compositionality33%

Counting11%

Negation22%

Relative Position33%

Scale & Proportions33%

Human realism

37%

Faces & Expressions25%

Full Body17%

Hands25%

Multi-Subject50%

Professional Studio

39%

Camera & Lighting33%

Color Precision33%

Photorealism33%

Graphical design

34%

Data Visualisation33%

Layout & Design22%

Style Diversity33%

Truthfulness

43%

Photorealism0%

Physics & Reflections50%

World Knowledge25%