Upload 2765290/3113284/README.md with huggingface_hub

2765290/3113284/README.md

@@ -0,0 +1,94 @@
+---
+license: other
+tags:
+- concept
+- nsfw
+- scene change
+- scene cut
+- scene jump
+- seamless
+---
+
+# Wan 2.2 SCS for NSFW - Scene Change System for NSFW - ass_to_mouth_a - 3113284
+
+**Model Type**: LORA
+
+**Base Model**: Wan Video 2.2 T2V-A14B
+
+**Trigger Words**: None
+
+**Tags**: concept, nsfw, scene change, scene cut, scene jump, seamless
+
+## Gallery
+
+<table>
+  <tr>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2ef3fc8f-955c-47c1-8351-b501c4c88244/original=true/136199194.mp4" width="200" controls muted autoplay loop></video></td>
+  </tr>
+</table>
+
+## Description
+
+### about SCS(Scene Change System)
+
+This system utilizes the Wan2.2 I2V workflow in conjunction with Scene Change LoRA and T2V LoRA, enabling a seamless transition to the T2V LoRA scene while preserving the person from the input image.
+
+Scene transitions using this system offer exceptional character consistency. You no longer need to train a character LoRA every time; a single portrait image is all it takes.
+
+### Files required for SCS and their roles
+
+1. Scene Change LoRA(scene\_change\_nsfw\_v2.0\_high\_noise.safetensors)
+
+This LoRA serves to seamlessly guide the input image into a T2V scene. It does not use Low Noise.
+
+2. Target T2V LoRA
+
+This is a T2V LoRA designed for the target scene. The "High Noise" setting strongly anchors the scene, while the "Low Noise" setting provides the foundation for rendering the genitals. I recommend using the official T2V created by MQ Lab.
+
+3. DR34ML4Y\_I2V\_14B\_LOW\_v2
+
+This renders genitals. High Noise is not used.
+
+<https://civitai.red/models/1811313/dr34ml4y-all-in-one-nsfw-wanltx2?modelVersionId=2553271>
+
+### Strength setting
+
+From the perspective of character consistency, the lowest strength at which each LoRA can effectively fulfill its role is preferable.
+
+scene\_change\_nsfw\_v2.0\_high.safetensors 0.70
+
+target\_t2v\_high.safetensors 0.70
+
+target\_t2v\_low.safetensors 0.60
+
+DR34ML4Y\_I2V\_14B\_LOW\_V2.safetensors 1.00
+
+### Prompting
+
+Please refer to the page for each T2V LoRA.
+
+### Input image
+
+I recommend square-resolution, portrait images.
+
+### Others
+
+Using the 4-step LoRA and generating with "High Noise 4-step" and "Low Noise 4-step" yields the highest quality.
+
+You can get the latest development updates from my Discord server.
+
+<https://discord.gg/hs4kDREXa6>
+
+I am asking for donations from those who wish to support my work on Fanvue. Please consider supporting me so that I can continue creating.
+
+<https://www.fanvue.com/mq-lab>
+
+---
+
+Author: [MQ_Lab](https://civitai.com/user/MQ_Lab)
+
+Model: [CivitAI Model Page](https://civitai.com/models/2765290?modelVersionId=3113284)
+
+Archive: [CivArchive Page](https://civarchive.com/models/2765290?modelVersionId=3113284)
+
+<!-- Version: 20260709_upload -->