Upload 3008073/3453190/README.md with huggingface_hub

3008073/3453190/README.md

@@ -0,0 +1,127 @@
+---
+license: other
+tags:
+- concept
+- nsfw
+- nude
+- vagina
+---
+
+# Moss Image - Better Nude - v3.0 - 3453190
+
+**Model Type**: LORA
+
+**Base Model**: MOSS Image
+
+**Trigger Words**: None
+
+**Tags**: concept, nsfw, nude, vagina
+
+## Gallery
+
+<table>
+  <tr>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c8fc5bf5-55c2-4da1-9ef4-6f3a30b2cdd0/original=true/148146048.jpeg" width="200"></td>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/dc07658d-1973-487a-9e4e-a83fae999642/original=true/148146065.jpeg" width="200"></td>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e0778c7e-f08e-4852-b83d-26ef13e7da35/original=true/148142417.jpeg" width="200"></td>
+  </tr>
+  <tr>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/e2cd5c7e-878f-48ef-93c9-ed65b8767fe9/original=true/148146247.jpeg" width="200"></td>
+    <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/eaa76822-7b73-483f-ac56-9bea3a0d595e/original=true/148054193.jpeg" width="200"></td>
+  </tr>
+</table>
+
+## Description
+
+### **Update: fixed over-bright 8-step images**
+
+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: [Image1](https://civitai.red/images/148112265) and [Image2](https://civitai.red/images/148112282)  
+  
+Please re-download [**moss\_pussy\_lora\_v3.0\_8steps.safetensors**](https://civitai.red/api/download/models/3452414?fileId=3354846) and [**moss\_pussy\_lora\_v3.0\_8steps\_dmd2\_only.safetensors**](https://civitai.red/api/download/models/3452414?fileId=3354845). The other two files are unchanged.  
+  
+  
+**MOSS Better Nude LoRA v3.0**
+
+I 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:
+
+* [**moss\_pussy\_lora\_v3.0.safetensors**](https://civitai.red/api/download/models/3453190?fileId=3353880): 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)
+* [**moss\_pussy\_lora\_v3.0\_8steps\_dmd2\_only.safetensors**](https://civitai.red/api/download/models/3452414?fileId=3354845): 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)
+* [**moss\_pussy\_lora\_v3.0\_face.safetensors**](https://civitai.red/api/download/models/3453190?fileId=3353863): 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)
+* [**moss\_pussy\_lora\_v3.0\_8steps.safetensors**](https://civitai.red/api/download/models/3452414?fileId=3354846): 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。)
+
+**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**
+
+* Model: MOSS-Image Base
+* 8 steps, separate files: 8steps\_dmd2\_only 1.0 → v3.0 1.0 → face 0.8, [workflow](https://civitai.red/api/download/models/3453190?fileId=3353610)
+* 8 steps, all-in-one: v3.0\_8steps 1.0 only. Don't add the other three on top, [workflow](https://civitai.red/api/download/models/3452414?fileId=3352660)
+* Both 8-step setups: 8 steps, CFG 1, euler + simple
+* 50 steps: v3.0 (+ face if you want it) without the 8-step LoRA, CFG ~3, [workflow](https://civitai.red/api/download/models/3453190?fileId=3353609)
+
+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:
+
+* **Retrained the pussy LoRA with every face masked out of the loss.** It learns anatomy and body detail only, not faces.
+* **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).
+* **Face LoRA added after distillation**, so it shapes the look of the face without being collapsed into a single identity.
+* Everything is merged into one 8-step LoRA.
+
+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**
+
+* Model: MOSS-Image **Base**
+* LoRA strength 1.0. Don't add another 8-step / DMD LoRA, because it's already included.
+* 8 steps, CFG 1, euler + simple
+
+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.
+
+* **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.
+* **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 `modelopt.torch.fastgen` DMD implementation.
+* **Use:** MOSS-Image-Base, 8 steps, CFG 1, euler / **simple** scheduler (the schedule it was distilled on).
+
+**Credits:** Huge thanks to **lodestones** for the original 8-step DMD/DMD2 LoRAs ([MOSS-Image-Base-8-steps-dmd](https://huggingface.co/lodestones/MOSS-Image-Base-8-steps-dmd), [Kromoss](https://huggingface.co/lodestones/Kromoss)), which this is fine-tuned from, to **NVIDIA** for the open DMD2 code in [Model-Optimizer](https://github.com/NVIDIA/Model-Optimizer).  
+  
+  
+V2.0 added more sex scenes  
+V2.0 face + pussy merged moss\_face\_regface\_v2.safetensors to V2.0
+
+workflow.json attached  
+Check this post (<https://civitai.red/posts/31908504>) 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
+
+---
+
+Author: [salttaro](https://civitai.com/user/salttaro)
+
+Model: [CivitAI Model Page](https://civitai.com/models/3008073?modelVersionId=3453190)
+
+Archive: [CivArchive Page](https://civarchive.com/models/3008073?modelVersionId=3453190)
+
+<!-- Version: 20261108_upload -->