Modelpublic

QuantStack/MAGREF_Wan2.1_I2V_14B-GGUF

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

12likes300downloads

Model Card

This is a GGUF conversion of MAGREF-Video/MAGREF.

All quantized versions were created from the base FP16 model using the conversion scripts provided by city96, available at the ComfyUI-GGUF GitHub repository.

Usage

The model files can be used in ComfyUI with the ComfyUI-GGUF custom node. Place the required model(s) in the following folders:

Type	Name	Location	Download
Main Model	MAGREFWan2.1I2V_14B-GGUF	`ComfyUI/models/unet`	GGUF (this repo)
Text Encoder	umt5-xxl-encoder	`ComfyUI/models/text_encoders`	Safetensors / GGUF
CLIP Vision	clipvisionh	`ComfyUI/models/clip_vision`	Safetensors
VAE	Wan21VAE_bf16	`ComfyUI/models/vae`	Safetensors

**ComfyUI example workflow**

Demos

<table border="1"> <tr> <th colspan="2" align="center">Input</th> <th align="center">Output</th> </tr> <tr> <td align="center"> <img src="demo/001/1.jpeg" style="max-height: 480px;" alt="Reference Image 1"> </td> <td align="center"> <img src="demo/001/2.jpeg" style="max-height: 480px;" alt="Reference Image 2"> </td> <td align="center"> <img src="demo/001/magref14b00001.webp" style="max-height: 480px;" alt="Generated Output"> </td> </tr> <tr> <td colspan="3" align="center"> Two men taking a selfie together in an indoor setting. One of them, with a bright and expressive smile, holds the smartphone at arm’s length to frame the shot. He has voluminous, natural-textured hair and appears enthusiastic and energetic. Standing beside him is another man with neatly styled hair and a composed expression, wearing a white athletic jersey with black accents. </td> </tr> </table>

Notes

All original licenses and restrictions from the base models still apply.

Reference

—For an overview of quantization types, please see the GGUF quantization types.