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 ImageBench V1 run.

local/sefi-image-2b-turbo

Local

SeFi Image 2B Turbo is a locally fine-tuned text-to-image model produced by the SeFi image-generation fine-tuning pipeline and run on an NVIDIA DGX Spark. It is the ~2B turbo (few-step) variant of the SeFi Image family. It is not a publicly released hosted product; no external model card or citation is disclosed.

Maker: SeFi pipeline
Family: SeFi Image
Model Size: ~2B
estimated
Cost: local run; no API price
not_applicable
Run Target: gx10/sefi-image-2b-turbo
Effective Request: Effective request fields unknown