A 5.6B open-weights model that runs on 8GB consumer GPUs and handles generation, editing and up to 10 reference images makes local and self-hosted image pipelines practical. Builders can fine-tuningTaking a trained model and training it a bit more on your own examples so it gets better at one specific job.Full definition → the base model or use the distillationTraining a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.Full definition → one for low latency.
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.
fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
