<h3 id="z-image-turbo-&quot;de-distilled&quot;">Z-Image Turbo "de-distilled"</h3>This is a LoRA for fun. Until z-image base model released."de-distill" a distilled model is a stupid idea, but ... still no z-image base.¯\(°_o)/¯Now I can use CFG (and negative prompt) again, like a normal model.Better details? Higher contrast? Seems a little bit.Technically there is no such thing called "de-distilled". What the model learned is learned. This LoRA just make the "distilled" model act more like a normal model so that using CFG won't burn the image. I don't know how to name it.Trained with ~10k images with lr 0.00001. 1 epoch only.<hr />Technically this is also a "adapter" and you can train LoRA on top of it.Differences with <a target="_blank" rel="ugc" href="https://huggingface.co/ostris/zimage_turbo_training_adapter/tree/main">ostris's adapter:</a><ul><li>real images, no repeat, rather than self-generated images</li><li>less trained (10k steps vs 57k steps)</li></ul>Haven't tried to training a lora on this yet. I just want CFG for now.

Files with SHA256: b5927e6ec41464817e6083b990baa1d6f3dce26c03a1f6d49c1e90cabc4a6b0f