LoRA Weight: 0.7-0.8 Model Features This is a DistillLoRA for Z-Image, which can distill to 2 steps and CFG. It does not use any Z-Image-Turbo-related weights and is trained from scratch. It is compatible with other Z-Image LoRAs and control systems. This model will slightly reduce output quality and alter the model's output composition. Please refer to the results section for specific comparisons. The purpose of this model is to provide fast generation compatibility for Z-Image derivative models, rather than replacing Z-Image-Turbo.