Upload 2649114/2974561/README.md with huggingface_hub

2649114/2974561/README.md

@@ -0,0 +1,122 @@
+---
+license: other
+tags:
+- action
+---
+
+# Forced BJ - HighN - 2974561
+
+**Model Type**: LORA
+
+**Base Model**: Wan Video 2.2 I2V-A14B
+
+**Trigger Words**: ysp_forcbj24, man comes in from the right naked holding his penis, man aggressively grabs woman's head and inserts his penis into her mouth, woman performs rhythmic bobbing motion on his penis, man's hand on woman's head, woman's eyes closed, close-up face view, soft indoor lighting, static camera
+
+**Tags**: action
+
+## Gallery
+
+<table>
+  <tr>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c3850b6d-1414-4f1c-a2b1-2a11bc5817e0/original=true/131736629.mp4" width="200" controls muted autoplay loop></video></td>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/065d9ac6-2958-4740-96af-47ec2b48aec2/original=true/131736947.mp4" width="200" controls muted autoplay loop></video></td>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/92e4a3ff-533c-430c-b814-b3b2c02e6519/original=true/131736948.mp4" width="200" controls muted autoplay loop></video></td>
+  </tr>
+</table>
+
+## Description
+
+Trained on <https://yorespot.com> — where creators train faster, cheaper, and with minimal censorship (within legal limits). If you’re serious about building models, that’s where you should be.
+
+---
+
+WAN 2.2 I2V LoRA
+
+========================================================
+
+Trigger Word
+------------
+
+ysp\_forcbj24
+
+---
+
+Overview
+
+This is a dual-expert WAN 2.2 I2V LoRA trained for high-quality portrait video generation. It uses a two-phase training approach to properly separate low-noise detail learning and high-noise motion structure — resulting in cleaner motion, stronger consistency, and better frame coherence than single-pass LoRAs.
+
+---
+
+Training Details
+
+Base Model:  
+• WAN 2.2 I2V 14B  
+• Dual-expert setup (LOW + HIGH LoRA files)
+
+Method:  
+• Musubi Tuner video LoRA workflow  
+• Two-phase training (LOW timesteps → HIGH timesteps)
+
+Dataset:  
+• 16 portrait video clips (512×512)  
+• Hand-captioned (.txt per clip)  
+• Full frame extraction (~30 FPS)  
+• Up to 33 frames per clip  
+• 4 repeats per clip
+
+Training Config:  
+• LoRA rank: 32  
+• Alpha: 32  
+• Learning rate: 2e-4  
+• Optimizer: AdamW (8-bit)  
+• Scheduler: Cosine  
+• Precision: bf16 + gradient checkpointing
+
+Training Process:  
+• 50 epochs (LOW noise model)  
+• 50 epochs (HIGH noise model)  
+• Total: 100 effective passes across both experts
+
+Training Time:  
+• ~20 hours total runtime
+
+---
+
+Recommended Usage (IMPORTANT)
+
+This is a dual-LoRA system. You MUST use both files together.
+
+HIGH noise LoRA:  
+• Strength: 0.55
+
+LOW noise LoRA:  
+• Strength: 0.90
+
+Best results come from using both simultaneously in a WAN 2.2 I2V workflow (ComfyUI dual-slot setup).
+
+Using only one will significantly reduce quality.
+
+---
+
+Why This Matters
+
+Most LoRAs fail at motion consistency or overfit to static detail. This setup avoids that by splitting the learning problem:
+
+• LOW model → structure, identity, fine detail  
+• HIGH model → motion, transitions, temporal coherence
+
+The result is smoother, more stable, and more realistic video output.
+
+---
+
+If you want to train models like this yourself — faster, cheaper, and without the usual platform limitations — train at <https://yorespot.com>.
+
+---
+
+Author: [YoReSpot](https://civitai.com/user/YoReSpot)
+
+Model: [CivitAI Model Page](https://civitai.com/models/2649114?modelVersionId=2974561)
+
+Archive: [CivArchive Page](https://civarchive.com/models/2649114?modelVersionId=2974561)
+
+<!-- Version: 20260525_upload -->