ImageBench

vs

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 ImageBench V1 run.

local/boogu-image-turbo

Local

Boogu-Image-0.1-Turbo is Boogu's 10B Apache-2.0 open-source text-to-image turbo model, a four-step distilled variant focused on fast 1K generation, photorealism, prompt adherence, and Chinese-English text rendering.

Maker
Boogu
Family
Boogu-Image-0.1
Model Size
10B
high
Cost
local run; no API price
not_applicable
Run Target
gx10/boogu-image-turbo
Effective Request
response_format: b64_json · size: 1024x1024 · num_inference_steps: 4
Sources
Boogu-Image-0.1-Turbo model cardBoogu-Image-0.1 ComfyUI workflow

fal/microsoft/mai-image-2.5

API

MAI-Image-2.5 is Microsoft AI’s flagship photorealistic text-to-image and editing model, built for high-quality generation and controllable, identity-preserving edits at production scale. Strong at readable embedded text, composition, and studio/product visuals; ships a faster MAI-Image-2.5-Flash variant. Places top-3 on Arena.ai T2I. Note: a strict content filter refuses some benign prompts (e.g. involving children).

Maker
Microsoft
Family
MAI-Image
Model Size
not disclosed
unknown
Cost
~$0.05 / image
medium
Run Target
fal/microsoft/mai-image-2.5
Effective Request
aspect_ratio: 1:1 · num_images: 1 · output_format: png
Sources
MAI-Image-2.5 (Text to Image) on falMicrosoft Foundry Labs — MAI-Image-2.5
61.9vs65.7
Overall
57%vs65%
Capability
66.6vs66.8
Est. Preference
9.9svs25.4s
Avg Latency
Text Rendering80%80%Spatial Reasoning58%77%Human realism31%33%Truthfulness48%44%Professional Studio82%85%Graphical design71%79%Preference67%67%Latency33%5%

All 192 generations

Text Rendering80%vs86%

local/boogu-image-turbofal/microsoft/mai-image-2.5

Typography Style100%vs100%

Writing accuracy75%vs82%

Spatial Reasoning58%vs79%

local/boogu-image-turbofal/microsoft/mai-image-2.5

Attributes Binding78%vs89%

Compositionality67%vs89%

Counting22%vs56%

Negation33%vs78%

Relative Position75%vs83%

Scale & Proportions67%vs75%

Human realism31%vs35%

local/boogu-image-turbofal/microsoft/mai-image-2.5

Faces & Expressions75%vs91%

Full Body8%vs0%

Hands8%vs0%

Multi-Subject33%vs67%

Truthfulness48%vs44%

local/boogu-image-turbofal/microsoft/mai-image-2.5

Photorealism33%vs67%

Physics & Reflections67%vs42%

World Knowledge33%vs42%

Professional Studio81%vs85%

local/boogu-image-turbofal/microsoft/mai-image-2.5

Camera & Lighting83%vs75%

Color Precision92%vs92%

Photorealism33%vs100%

Graphical design71%vs83%

local/boogu-image-turbofal/microsoft/mai-image-2.5

Data Visualisation0%vs33%

Layout & Design67%vs89%

Style Diversity92%vs91%