Wan 2.2 I2V A14B DISTILL LIGHTX2V 4STEP GGUF

--- base_model: - lightx2v/Wan2.2-Distill-Models tags: - image-to-video - video-generation - gguf --- Quantized GGUF versions of the [Wan2.2 Distill Models](https://huggingface.co/lightx2v/Wan2.2-Distill-Models) by the LightX2V team. ### 📂 Available High Noise Models | Model | Release Date | Description | |--------|--------------|-------------| | **`high_noise_260412`** | 🗓️ Apr 12, 2026 | 🔹 **Latest high noise model** | | `high_noise_1030` | 🗓️ Oct 30, 2025 | Previous high noise model | | `high_noise` | 🗓️ Oct 17, 2025 | Previous high noise model | ### 📂 Available Low Noise Models | Model | Release Date | Description | |--------|--------------|-------------| | **`low_noise_260412`** | 🗓️ Apr 12, 2026 | 🔹 **Latest low noise model** | | `low_noise` | 🗓️ Oct 17, 2025 | Latest low noise model | ### 🎬 Side-by-Side Comparison of the Latest Model 260412 FP32, BF16, Q8, Q4_K_S, Q2_K ### Model Information Check out the original [LightX2V Model Card](https://huggingface.co/lightx2v/Wan2.2-Distill-Models) for detailed information about the model. ### Usage The model can be used with: - [**ComfyUI-GGUF**](https://github.com/city96/ComfyUI-GGUF) by **city96** - [**ComfyUI-WanVideoWrapper**](https://github.com/kijai/ComfyUI-WanVideoWrapper) by **kijai** *(make sure you're on the latest version)* ### Credits - **Original Model**: [LightX2V Team](https://huggingface.co/lightx2v) - **Quantization Tools & Guide**: [llama.cpp](https://github.com/ggml-org/llama.cpp) & [city96](https://github.com/city96/ComfyUI-GGUF/blob/main/tools/README.md) ### License This repository follows the same license as the [Wan2.2-Distill-Models](https://huggingface.co/lightx2v/Wan2.2-Distill-Models).