An open image model that adds bounding-box layout control and runs in about 2 seconds on an H100, with NVFP4 and FP8 weights for smaller GPUs and a modular pipeline you can extend.
Terms in this piece · Glossary
distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
LoRA — A cheap way to fine-tune a model by training a small add-on layer instead of changing all of the model's weights.
