Upload 2656888/2983380/README.md with huggingface_hub

2656888/2983380/README.md

@@ -0,0 +1,127 @@
+---
+license: other
+tags:
+- character
+---
+
+# SmashCut SpitRoast - High - 2983380
+
+**Model Type**: LORA
+
+**Base Model**: Wan Video 2.2 I2V-A14B
+
+**Trigger Words**: ysp_spliroa12, hard cut with no smooth transition jumps straight into spitroast position, woman instantly on her hands and knees between two men, she bobs her head back and forth on the man in front while the man behind grips her hips and thrusts from behind, her torso rocks forward and back in steady rhythmic motion, woman alone in opening frame, both men already present after cut, close-up face view, man's penis in foreground, static camera
+
+**Tags**: character
+
+## Gallery
+
+<table>
+  <tr>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d8734c12-a6c5-4614-9fd4-836aa2f9c207/original=true/132061796.mp4" width="200" controls muted autoplay loop></video></td>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7e04442e-adff-4170-b875-47a3a0a92d41/original=true/132061920.mp4" width="200" controls muted autoplay loop></video></td>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/14ed4c1d-f0de-40a6-ac83-eb0f62cee0e7/original=true/132061921.mp4" width="200" controls muted autoplay loop></video></td>
+  </tr>
+  <tr>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/95967fb8-706b-4b2b-a9dc-d6bb7ac08916/original=true/132061923.mp4" width="200" controls muted autoplay loop></video></td>
+  </tr>
+</table>
+
+## Description
+
+PLEASE FOR THE LOVE OF EVERYTHING GOOD POST YOUR RESULTS!
+
+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\_spliroa12,
+
+---
+
+Overview
+
+This is a 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  
+• (LOW + HIGH LoRA files)
+
+Method:  
+• Musubi Tuner video LoRA workflow  
+• Two-phase training (LOW timesteps → HIGH timesteps)
+
+Dataset:  
+• 25 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.
+
+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/2656888?modelVersionId=2983380)
+
+Archive: [CivArchive Page](https://civarchive.com/models/2656888?modelVersionId=2983380)
+
+<!-- Version: 20260528_upload -->