Create Uncensored Videos with Wan2.2 Remix in ComfyUI (I2V)

Creating cinematic video clips from text prompts has never been easier, thanks to the new WAN 2.2 Remix model. This innovative model is designed specifically for generating high-quality, NSFW-themed videos without the need for additional LoRA setups. With its focus on human dynamics, realistic motion, and scene consistency, Wan2.2 Remix produces lifelike movements and smooth transitions that can elevate your creative projects. In this tutorial, we will guide you through the process of setting up and using the WAN 2.2 Remix model in ComfyUI, ensuring you can harness its full potential for your image to video generation needs. We will cover everything from installation requirements to detailed workflow configurations, and even provide example outputs to inspire your creativity. Whether you are a seasoned creator or just starting, this guide will help you navigate the exciting world of AI-driven video generation.

⚠️ Important: This tool should be used responsibly. It is the user’s responsibility to ensure ethical and legal use of the model.

Before starting, make sure your system meets the hardware and software requirements to run the WAN 2.2 Remix Video Generation Model in ComfyUI. This model benefits from strong GPU performance — we recommend an RTX 4090 (24GB VRAM) or using RunPod for cloud-based GPU access.

Requirement 1: ComfyUI Installed

To begin, you’ll need ComfyUI installed either locally or on a cloud service.If you're installing locally on Windows, follow this guide:

👉 How to Install ComfyUI Locally on Windows

If you don’t have a powerful GPU available, consider running ComfyUI on RunPod using a persistent network volume. For a step-by-step walkthrough, you can check out the dedicated article and accompanying YouTube video linked below.

👉 How to Run ComfyUI on RunPod with Network Volume

Requirement 2: Download Models for Wan2.2 Remix (I2V)

Download the necessary model files and place them in the correct directories within ComfyUI. The table below lists the required files, as well as optional Lightning LoRAs that can speed up video generation—but keep in mind they may slightly reduce quality, so using them is up to you.

Verify Folder Structure

Confirm that your folders and files look like this:

ts
1📁 ComfyUI/
2└── 📁 models/
3    ├── 📁 text_encoders/
4    │   └── nsfw_wan_umt5-xxl_fp8_scaled.safetensors
5    ├── 📁 diffusion_models/
6    │   ├── Wan2.2_Remix_NSFW_i2v_14b_high_lighting_v2.0.safetensors
7    │   └── Wan2.2_Remix_NSFW_i2v_14b_low_lighting_v2.0.safetensors
8    ├── 📁 vae/
9    │   └── wan_2.1_vae.safetensors
10    └── 📁 loras/
11        ├── Wan2.2-Lightning_I2V-A14B-4steps-lora_HIGH_fp16.safetensors   (optional)
12        └── Wan2.2-Lightning_I2V-A14B-4steps-lora_LOW_fp16.safetensors    (optional)

Once all files are properly placed and organized, you’re ready to load the Wan2.2 Remix workflow in ComfyUI and begin generating videos. Optional Lightning LoRAs can be used to speed up the process, though they may slightly reduce quality. First, however, we need to download the workflow. Let’s move on to the next section!

With your environment and model files in place, the next step is to download and load the Wan2.2 Remix NSFW JSON workflow into ComfyUI. This workflow is essential for configuring the model and ensuring it runs correctly for image-to-video generation.

Step 1: Download the Workflow File

Begin by downloading the workflow file specifically designed for the Wan2.2 Remix NSFW model. This file contains all the nodes, model references, and configurations needed for the workflow to function properly. You can find the download link below:

👉 Download Wan2.2 Remix NSFW Workflow JSON

Step 2: Load the Workflow in ComfyUI

After downloading the workflow file, open ComfyUI and simply drag and drop the .json file onto the canvas. This will load the full setup and allow you to start working with the model immediately.

You can optionally enable the Lightning LoRAs within the workflow to speed up video generation. This may slightly reduce output quality. If you use these LoRAs, set the blue nodes: steps to 4 and split_step to 2 for optimal results.

You can also use our Next Diffusion – ComfyUI SageAttention Template on RunPod, which can further speed up rendering by 10–20% when sageattn is selected within the Load Models nodes:

In the next section, we’ll cover all the essential workflow settings to run the Wan2.2 Remix NSFW image-to-video model smoothly and efficiently.

Before generating videos, make sure your Wan2.2 Remix NSFW workflow has all models loaded. Optional Lightning LoRAs can speed up rendering, while resolution, steps, and split steps affect output quality and VRAM usage. Frame interpolation is applied last for smoother motion. To achieve dynamic movements and cinematic effects, be sure to provide a well-crafted prompt.

✅ Quick Tips:

• Lightning LoRAs speed up renders with only minor quality loss.

• Frame interpolation is optional but helps smooth high-FPS outputs.

With this setup, your Wan2.2 Remix NSFW workflow is ready for fast and flexible image to video generation. Load your images and start creating!

Below is an example video generated using the Wan2.2 Remix model. While we are unable to showcase full nudity or more sensual content here, we can assure you that this model works magic with uncensored material. For the moment, the example below highlights its capacity for smooth motion, natural movement, and cinematic framing.

Feel free to experiment on your own and explore the full creative potential of the model!

In this tutorial, we explored the powerful capabilities of the Wan2.2 Remix NSFW model for generating cinematic video clips from images and text prompts. By following the steps outlined, you should now be able to set up your environment, load the necessary models, and configure the workflow for smooth and efficient video generation.

The Wan2.2 Remix model excels at producing lifelike movements and smooth transitions, making it a strong choice for creators seeking high-quality NSFW-themed video content. Experimenting with different prompts, settings, and optional Lightning LoRAs will unlock a wide range of creative possibilities, enabling you to craft unique and engaging videos.

Happy creating and exploring the world of AI-driven video generation!