Skip to content

Wan 2.2 Image to Video (I2V & FLF2V)

Description

We will create a short 20s video using I2V and FLF2V techniques.

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 clip/
│   │   └── umt5-xxl-encoder-Q8_0.gguf
│   ├── 📂 loras/
│   │   ├── Wan2.2-I2V-A14B-lora-high_noise.safetensors
│   │   └── Wan2.2-I2V-A14B-lora-low_noise.safetensors
│   ├── 📂 unet/
│   │   ├── Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf
│   │   └── Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf
│   └── 📂 vae/
│       └── wan2.1_vae.safetensors

For I2V workflow use the WanImageToVideo node.

For FLF2V workflow use the WanFirstFrameLastFrame node.

Workflows

Prompt Initial Image Workflow
The luxury convertible car drives through a tropical mountainous valley during sunset. The car first speeds off down the road and the camera follows close behind. i2v-1 initial image i2v-1 workflow

WGET Commands

If you are using Runpod, or a similar hosted GPU service, then you can access your running pod/instance using a terminal.

#
#
# CD into ./ComfyUI/models/clip/ folder
wget https://huggingface.co/city96/umt5-xxl-encoder-gguf/resolve/main/umt5-xxl-encoder-Q8_0.gguf
#
#
#
# CD into ./ComfyUI/models/loras/ folder
wget https://huggingface.co/lightx2v/Wan2.2-Lightning/resolve/main/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1/high_noise_model.safetensors -O Wan2.2-I2V-A14B-lora-high_noise.safetensors
wget https://huggingface.co/lightx2v/Wan2.2-Lightning/resolve/main/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1/low_noise_model.safetensors -O Wan2.2-I2V-A14B-lora-low_noise.safetensors
#
#
#
# CD into ./ComfyUI/models/unet/ folder
wget https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/resolve/main/HighNoise/Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf
wget https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/resolve/main/LowNoise/Wan2.2-I2V-A14B-LowNoise-Q8_0.gguf
#
#
# CD into ./ComfyUI/models/vae/ folder
wget https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors

Wait for files to download fully before running your workflows.