<h3 id="update:-fixed-over-bright-8-step-images">Update: fixed over-bright 8-step images</h3>The text prompts I used during distillation never described lighting, so the 8-step LoRA learned to brighten every image toward a bright studio look, ignoring the lighting in your prompt. I re-distilled it with lighting descriptions added to those training prompts, and dark and moody scenes now stay dark. Examples: <a target="_blank" rel="ugc" href="https://civarchive.com/images/148112265">Image1 </a>and <a target="_blank" rel="ugc" href="https://civarchive.com/images/148112282">Image2</a> Please re-download <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3452414?fileId=3354846">moss_pussy_lora_v3.0_8steps.safetensors</a> and <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3452414?fileId=3354845">moss_pussy_lora_v3.0_8steps_dmd2_only.safetensors</a>. The other two files are unchanged. MOSS Better Nude LoRA v3.0I realized one merged file isn't very user-friendly, so v3.0 is uploaded as three separate LoRAs that you stack yourself, plus an all-in-one file for convenience:<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3453190?fileId=3353880">moss_pussy_lora_v3.0.safetensors</a>: The pussy / body LoRA. Every face was masked out during training (face loss = 0), so it learns anatomy only and leaves faces to the base model. (阴部 / 身体 LoRA。训练时所有人脸都被遮掉了（脸部 loss 为 0），所以它只学解剖结构，脸交给底模来生成)</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3452414?fileId=3354845">moss_pussy_lora_v3.0_8steps_dmd2_only.safetensors</a>: The 8-step speed-up only. Fine-tuned from lodestones' DMD2 specifically for v3.0, so it works best paired with v3.0. (只负责 8 步加速。在 lodestones 的 DMD2 基础上专门为 v3.0 微调过，所以最好搭配 v3.0 使用)</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3453190?fileId=3353863">moss_pussy_lora_v3.0_face.safetensors</a>: Optional face LoRA. Swap it for any face LoRA you like. (only Asian faces in this lora) (可选的人脸 LoRA，可以换成任何你喜欢的人脸 LoRA)</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3452414?fileId=3354846">moss_pussy_lora_v3.0_8steps.safetensors</a>: All-in-one 8-step LoRA: 8steps_dmd2_only 1.0 + v3.0 1.0 + face 0.8 in a single file. Use it alone at strength 1.0. (8 步合一版。等于 8steps_dmd2_only 1.0 + v3.0 1.0 + face 0.8 合并成一个文件，单独使用，强度 1.0。)</li></ul>Why a separate face LoRA? Because faces were masked out when training the pussy LoRA, faces now come straight from MOSS Base. That brings back face diversity: you no longer get the same face every time. But it also means there's no aesthetic push, so faces aren't always pretty. (Earlier I swapped faces with Z-Image, which pulls everything toward the same "beautiful" look.) The face LoRA nudges faces toward a more attractive look while keeping them varied. It's added after distillation, so it doesn't collapse into one identity. Use it, lower it, or replace it with your own.Usage<ul><li>Model: MOSS-Image Base</li><li>8 steps, separate files: 8steps_dmd2_only 1.0 → v3.0 1.0 → face 0.8, <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3453190?fileId=3353610">workflow</a></li><li>8 steps, all-in-one: v3.0_8steps 1.0 only. Don't add the other three on top, <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3452414?fileId=3352660">workflow</a></li><li>Both 8-step setups: 8 steps, CFG 1, euler + simple</li><li>50 steps: v3.0 (+ face if you want it) without the 8-step LoRA, CFG ~3, <a target="_blank" rel="ugc" href="https://civarchive.com/api/download/models/3453190?fileId=3353609">workflow</a></li></ul>Credit: 8-step base distill by lodestones (DMD2). v3.0 — 8 steps What changed from v2.0 (8 steps) In v2.0 the face LoRA was part of the teacher during distillation. DMD distillation is mode-seeking, so it collapsed the face LoRA into one dominant face, and most generations ended up with the same face.v3.0 fixes this:<ul><li>Retrained the pussy LoRA with every face masked out of the loss. It learns anatomy and body detail only, not faces.</li><li>New 8-step distillation: fine-tuned from lodestones' DMD2 LoRA, using Base + the new pussy LoRA as the teacher (no face LoRA in the teacher).</li><li>Face LoRA added after distillation, so it shapes the look of the face without being collapsed into a single identity.</li><li>Everything is merged into one 8-step LoRA.</li></ul>Result: faces are diverse again across seeds, while the genital detail at 8 steps is closer to the 50-step model than plain DMD2.Usage<ul><li>Model: MOSS-Image Base</li><li>LoRA strength 1.0. Don't add another 8-step / DMD LoRA, because it's already included.</li><li>8 steps, CFG 1, euler + simple</li></ul>Credit: 8-step base distill by lodestones (DMD2) How V2.0 8-steps version was made：This is an 8-step version of my moss_pussy_lora_v2.0, re-distilled so the fast sampler matches the full 50-step look.<ul><li>Teacher: MOSS-Image-Base with my v2.0 face + pussy LoRAs merged at 1.0, sampled at 50 steps, CFG 3, with skip-layer guidance on block 22.</li><li>Student: initialized from lodestones' 8-step DMD2 LoRA, then trained with DMD2 distribution matching for 300 student updates on ~640 images from my dataset. Built on NVIDIA's open-source <code>modelopt.torch.fastgen</code> DMD implementation.</li><li>Use: MOSS-Image-Base, 8 steps, CFG 1, euler / simple scheduler (the schedule it was distilled on).</li></ul>Credits: Huge thanks to lodestones for the original 8-step DMD/DMD2 LoRAs (<a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/MOSS-Image-Base-8-steps-dmd">MOSS-Image-Base-8-steps-dmd</a>, <a target="_blank" rel="ugc" href="https://huggingface.co/lodestones/Kromoss">Kromoss</a>), which this is fine-tuned from, to NVIDIA for the open DMD2 code in <a target="_blank" rel="ugc" href="https://github.com/NVIDIA/Model-Optimizer">Model-Optimizer</a>. V2.0 added more sex scenes V2.0 face + pussy merged <span style="background-color:rgb(37, 38, 43);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:14px">moss_face_regface_v2.safetensors to V2.0 workflow.json attached Check this post (<a target="_blank" rel="ugc" href="https://civarchive.com/posts/31908504">https://civarchive.com/posts/31908504</a>) for sex scenes prompts. This LoRA was trained on MOSS-Image-Base and can also be used with MOSS-Image-SFT, but I find that the base model produces better results. Lora strength: 1.0 Steps: 25 or 50 CFG: 3 or 4 Sampler: euler or er_sde Scheduler: Simple or Beta Resolution: 1024x1536 or 1536x1024 Only Asian female in the dataset！ pussy lora for MOSS image

Moss Image - Better Nude

Re-distilled from lodestones' DMD2 with a face-masked pussy LoRA as the teacher and the face LoRA added only after distillation, so faces are no longer all the same.

Files with SHA256: 667b0fdce0caef95acfbc2730a7587044634c9bc907744b6c2529e28468faa73