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/kromoss-dmd2

Local

Kromoss is lodestones' Apache-2.0 full fine-tune of MOSS-Image-Base at 1024 px (704k images), a drop-in replacement for MOSS-Image-SFT with the same Qwen3.5-9B text encoder and FLUX.2 small-decoder VAE. This entry adds the 8-step DMD2 turbo LoRA (DMD continued with a GAN stage against real images), the variant the author recommends.

Maker: lodestones
Family: Kromoss (MOSS-Image)
Model Size: 5B
medium
Cost: local run; no API price
not_applicable
Run Target: gx10/kromoss-dmd2
Effective Request: response_format: b64_json · size: 1024x1024 · num_inference_steps: 8 · guidance_scale: 1 · seed: 7
Sources: lodestones/Kromoss model card MOSS-Image project page