WAN2.2 I2V LIGHTNING-Video-4-8step

WAN2.2 I2V LIGHTNING-Video-4-8step

Turns a still image into a short video with the Wan2.2 image-to-video model on a Gradio page, set up for quick runs of 4 to 8 steps. For creators who want to animate a picture in the browser.

Made by Saravutw on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: WAN2.2 I2V LIGHTNING-Video-4-8step is a Gradio page that animates a picture. I2V stands for image to video, and the page is built on the Wan2.2 image-to-video model. The name points to fast runs of 4 to 8 steps. You can open it in the browser with nothing to install.

Who it suits: It suits people who want to try image-to-video generation without setting up a machine, and developers who want to read how a Wan2.2 demo is put together.

Industry | Who uses it | How they use it | Example
Marketing | Content creators | Bring a still picture to life for a post | Load a product image and ask for a short clip
Design | Designers | Test motion ideas from a concept picture | Animate a single illustration
Media | Video editors | Make short moving inserts from stills | Try a photo as the first frame
Software | Python developers | Read how the Wan2.2 model is wired into a Gradio app | Look through app.py and aoti.py

Skip it if you want to make video from text alone, since this page starts from an image.

Where to use it:

• A web browser, on the Space's page at Hugging Face, which runs on ZeroGPU
• Your own Windows, macOS or Linux computer with Python

Use case | Who | What they get back
Animate a picture | Creators | A short generated video that starts from your image
Test a fast setting | Researchers | A result from a run of only a few steps
Study the demo | Developers | A small Gradio app with a model folder

How to set it up: The online page needs nothing. A local copy needs Python and two lists of packages.

• Python and pip
• Python packages from requirements.txt
• System packages from packages.txt, which the Space installs with apt-get
• Windows, macOS or Linux

1. Install the Hugging Face hub library.
2. Download the Space's files into a folder named WAN2.2_I2V_LIGHTNING_4-8step_custom.
3. Move into that folder.
4. Install Gradio 6.0.2, then the packages from requirements.txt.
5. Start app.py.

pip install -U huggingface_hub
hf download Saravutw/WAN2.2_I2V_LIGHTNING_4-8step_custom --repo-type space --local-dir WAN2.2_I2V_LIGHTNING_4-8step_custom
cd WAN2.2_I2V_LIGHTNING_4-8step_custom
pip install gradio==6.0.2
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page, or run the last command above for a local copy and open the address it prints. Give the page a starting image and let it generate the video.

python app.py

Example: You open the page and load one clear picture. The page generates a short video that starts from it, and you watch the result in the browser.

For newcomers and experts: Start with one clear picture of a single subject. The record has no README, so the controls are whatever the page itself shows.

The app is built with Gradio 6.0.2, and its main file is app.py. The Hugging Face copy runs on ZeroGPU hardware. The record names three models: the Wan2.2 image-to-video model in Diffusers form, a Wan transformer build and RIFE. The repository also holds aoti.py and a model folder. It does not say what RIFE or the transformer build do inside the pipeline.

Open the page
Give it a starting image
The Wan2.2 model runs on a ZeroGPU
Watch the video it returns

Good to know:

• Hardware: The Hugging Face copy runs on ZeroGPU hardware.
• Gaps: The source has no README, so settings, clip length and limits are not described here.
• MCP: Hugging Face lists the Space with an MCP tag. The source does not say how to connect to it.
• License: apache-2.
• Cost to run: none named.
• Data it reaches: The images you give it.

On Hugging Face, 13 November 2026

• Likes: 425
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/Saravutw/WAN2.2_I2V_LIGHTNING_4-8step_custom
• Files: https://huggingface.co/spaces/Saravutw/WAN2.2_I2V_LIGHTNING_4-8step_custom/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.