Innovate Futures @ Benji

Ditto in ComfyUI With Wan Vace - Transform ANY Video with Just a Text Prompt!

Added 2025-10-23 14:37:11 +0000 UTC

In this video, you’ll learn how to easily install and use the official Ditto models in ComfyUI to restyle your videos using only text prompts—no reference images needed. We walk through both the official GitHub workflow and native ComfyUI node setups, showing you how to load the Ditto Global Comfy model, configure LoRAs like COS V14B, and generate stunning style transfers while preserving original motion. This content is perfect for AI video creators, ComfyUI users, and digital artists who want fast, high-quality video restyling without complex workflows or ControlNet dependencies. With Ditto’s fine-tuned integration into WAN Video VAE, you can transform everyday footage into fantasy, pixel art, cartoon, or cinematic styles in minutes—making it a powerful tool for content creators, indie filmmakers, and AI enthusiasts looking to push creative boundaries efficiently.

From Ditto GitHub:

Using with ComfyUI

Note: While ComfyUI runs faster with lower computational requirements (832×480x73 videos need 11G GPU memory and ~4min on A6000), please note that due to the use of quantized and distilled models, there may be some quality degradation.

Environment Setup

First, follow the ComfyUI installation guide to set up the base ComfyUI environment. We strongly recommend installing ComfyUI-Manager for easy custom node management:

# Install ComfyUI-Manager cd ComfyUI/custom_nodes git clone https://github.com/Comfy-Org/ComfyUI-Manager.git

After installing ComfyUI, you can either:

Option 1 (Recommended): Use ComfyUI-Manager to automatically install all required custom nodes with the function Install Missing Custom Nodes.

Option 2: Manually install the required custom nodes (you can refer to this page):

Download Models

Download the required model weights from: Kijai/WanVideo_comfy to subfolders of models/. Required files include: