Upload 2653676/2979728/README.md with huggingface_hub

2653676/2979728/README.md

@@ -0,0 +1,116 @@
+---
+license: other
+tags:
+- style
+---
+
+# Minotaur Slam - HighNoise - 2979728
+
+**Model Type**: LORA
+
+**Base Model**: Wan Video 2.2 I2V-A14B
+
+**Trigger Words**: ysp_ruftst12, woman's face and body struggle in pain but she is aroused, woman's eyes open and mouth gasping, back deeply arched and body tensed, close-up face view, warm candlelit stone chamber lighting, slight handheld camera movement
+
+**Tags**: style
+
+## Description
+
+Very first credit for the idea comes from seeing [@Anaphiel](https://civitai.red/user/Anaphiel) 's Art! Wow Just Wow.
+
+Please Post Results! I want to see if your art turned out as good as mine.
+
+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\_ruftst12,
+
+---
+
+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:  
+• 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.
+
+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/2653676?modelVersionId=2979728)
+
+Archive: [CivArchive Page](https://civarchive.com/models/2653676?modelVersionId=2979728)
+
+<!-- Version: 20260527_upload -->