Wan 2.2 A14B I2V GGUF UPUP

# Optimize Workflow

### I rebuilt all of it, even though the original was consistent. Because I realized that my original was really messy !

### Remove the TAE decodes, remove the two-stage decodes, and they don't seem to be needed anymore.

### More detailed (though still to be enhanced) Easier to use, cleaner and more intuitive interface, and a better global picture.

Cool Title

# The model you need.

## Model Links

checkpoint

- [DaSiWa WAN 2.2 I2V 14B (High model)](/model/1981116?modelVersionId=2388548)

- [DaSiWa WAN 2.2 I2V 14B (Low model)](/model/1981116?modelVersionId=2388627)

text_encoders

- [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)

vae

- [wan_2.1_vae.safetensors](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors)

upscale_model

- [R-ESRGAN 4x+ Anime6B.pth

](https://huggingface.co/zelt54/RoNa/tree/main)

## Model Storage Location

```

📂 ComfyUI/

├── 📂 models/

│ ├── 📂 text_encoders/

│ │ └── umt5_xxl_fp8_e4m3fn_scaled.safetensors

│ ├── 📂 checkpoints/

│ │ └── dasiwa-wan2.2-i2v-lightspeed.safetensors

│ ├── 📂 vae/

│ │ └── wan_2.1_vae.safetensors

|____|____ _📂upscale_model/

|____R-ESRGAN 4x+ Anime6B.pth

```

# The customized nodes you need

[ https://github.com/rgthree/rgthree-comfy ]

[ https://github.com/yolain/ComfyUI-Easy-Use ]

[ https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite ]

[ https://github.com/cubiq/ComfyUI_essentials ]

[ https://github.com/Fannovel16/ComfyUI-Frame-Interpolation ]

[ https://github.com/Mobius-star/comfyui-useless-nodes ]