Skip to content

Wan 2.2 Image to Video (I2V & FLF2V)

Video Lecture

Section Video Links
Wan 2.2 Image To Video Wan 2.2 Image To Video Wan 2.2 Image To Video

Description

We will create a short 20s looping 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

Workflows

For I2V workflow use the WanImageToVideo node.

For FLF2V workflow use the WanFirstLastFrameToVideo node.

Prompt Initial Image Workflow
The woman drives the luxury convertible car through a tropical mountainous valley during sunset. The camera follows close behind the car as it speeds down the road. i2v-1 initial image i2v-1 workflow
The woman turns the car right down another road and quickly accelerates away. The camera follows close behind the car. The luxury convertible car is driving through a tropical mountainous valley during sunset.
The car is speeding down the road. The camera follows close behind the car. Tropical mountainous valley. Sunset.
The car is speeding down the road. The camera follows close behind the car. Tropical mountainous valley. Sunset. The car accelerates fast and the wheels spin leaving white smoke behind.
The car is speeding down the road. The camera follows close behind the car and then pans around to the woman driving. Tropical mountainous valley. Sunset.

Final Output

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 -c 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 -c https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/resolve/main/HighNoise/Wan2.2-I2V-A14B-HighNoise-Q8_0.gguf
wget -c 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 -c 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.