3/3/26 UPDATEI've uploaded a custom merge of the 2603 2-step lora and my key edit of the 2602 8-step lora. This has resulted in a nice, flexible distill that can generate great outputs from 4-10 steps. It has also helped the gridmarking artifacts that were visible at 1.0 strength with the 8-step 2602 UDCAI Edit lora. Please check it out!Original PostCredit to alibaba-pai for their fantastic work! This is a step and cfg distill lora to be applied to Z-Image base model and its derivatives. The lora has been converted to be compatible for use in ComfyUI.Best run at 8 steps with CFG 1. Avoid sageattention. Samplers that add noise per step such as LCM or dpmpp_SDE seem to work well.

Z-Image Fun Distill Lora

A new version update as of 2/10/2026 by Alibaba-PAI group! There is now an 8-step version and a 4-step version. Still recommend a strength around 0.7-0.8. Recommended samplers are the same.NOTE: There are additional keys in this version (feedforward) that when converted, results in bong_tangent failing to converge properly. Use other schedulers like linear quadratic, simple for now.

Files with SHA256: e387b79e994a72c51fd90b657ed8890e85ac93c9dd6ccbc588b6057edf95f445