<h1 id="moss-image-or-kouchan3-style-lora">Moss-Image | kouchan3 Style Lora</h1>BASE Model:Moss-Image-Base-bf16This is my first attempt at training a style LoRA for Moss. In actual inference, it isn't a 100% exact match—it captures about 80% of the original style.PS: Adding other style prompts or artist tags will cause style drift, so please keep that in mind when prompting.<h2 id="generation-and-settings">Generation &amp; Settings</h2>The showcase images were generated using <a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/MOSS-Image-Base-8-steps-dmd">DMD</a> distillation, which you can also download and try if you're interested. Alternatively, if you prefer not to use distillation, you can use the following standard inference settings:Sampler : EulerScheduler : Sgm_UniformStep: 35-50CFG: 3Base Model: Recommended to use the Base version for inference instead of the SFT version.<h1 id="krea-2-or-kouchan3-style-lora">Krea 2 | kouchan3 Style Lora</h1>BASE Model:Krea 2 RawTraining on ModelsSope

Files with SHA256: 4555248adfdea5fed092268b1e628dac9296c011d227820c56d2a2cc841de813