geceff/Wan2.2-Custom-Models-GGUF

Wan2.2 Custom GGUF (Tesla T4 Optimized)

This repository provides highly optimized Wan2.2 Image-to-Video (I2V) GGUF+LIGHNINGV2 and custom models. These variants are fine-tuned for running efficiently on memory-constrained environments, such as Google Colab equipped with an NVIDIA Tesla T4 GPU.

---

⚡ Optimal Settings for ComfyUI

To achieve perfect video motion without artifacts or image degradation (preventing fried or oversaturated visuals), we strongly recommend using the following parameters:

Parameter	Recommended Value	Note
Sampling Steps	4	When using Wan2.2 Lightning / Distilled V2
CFG Scale	1.0	Crucial for preventing burnt images
High Noise Steps	2 or 3	To lock in strong motion and structure before the Lightning layer clears noise
low Noise Steps	3 or `4
Sampler / Scheduler	euler + simple	Standard diffusion setup

*(Note for Higher Quality: If you want to achieve higher visual fidelity and enhance micro-details, it is highly recommended to use wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors as your final step. This hybrid approach significantly sharpens fine details and effectively eliminates motion blur during camera movements. This multi-step workflow is recommended for NVIDIA Tesla T4 GPUs or higher, and it can be seamlessly combined with any other GGUF High Noise models available in this repository.)

💾 Available Model Variants

Choose the right variant based on your creative workflow and VRAM configuration:

🔥 High Noise Models (wan2.2_i2v_high_noise_...)

• Best for: Creative, high-motion generation, and diverse camera movements.
• Available Quantizations: Q4_K_M, Q6_K_L, Q6_K, Q8_H

❄️ Low Noise Models (wan2.2_i2v_low_noise_...)

• Best for: High fidelity, generation stability, and strictly adhering to the prompt or structural layout of your starting frame.
• Available Quantizations: Q4_K_M, Q6_K_L, Q6_K, Q8_H, and fp8_scaled