Apps Page Background Image
Workflows/Wan 2.1 Squish LoRA Video

Wan 2.1 Squish LoRA Video

Save it for me
Operate
@
MimicPC
03/18/2025
ComfyUI
Popular & HOT
Video Generation
Wan 2.1
1 / 0
Detailed Introduction

Introduction

This is a creative workflow built on ComfyUI and deeply integrated with the WanVideo plug-in of Ali Tongyi Wanxiang. First, the "Load image" and "Load WanVideo to TextDecoder" nodes start the material loading and introduce the image and video materials into the workflow. Subsequently, multiple key nodes such as WanVideo Loader and WanVideo TextDecoder relay to complete the fine processing such as model loading and parameter configuration, giving new creative possibilities to the materials. Then, through the careful carving of color matching, image stitching and other links, the material achieves a gorgeous transformation from static to dynamic. Finally, after a series of operations, video synthesis is a natural result, bringing creators visual expressions beyond imagination.

This workflow has been optimized and expanded on the basis of WanVideo 2.1, with a new carefully developed LoRA module and an eye-catching squeeze effect. This innovative design significantly improves the visual expression of the video, adding more fun and creative dimensions to the content, making it more attractive and entertaining. Both the picture dynamics and the overall look and feel have become more vivid and interesting, bringing a refreshing experience to users.

https://github.com/Wan-Video/Wan2.1

https://huggingface.co/Kijai/WanVideo_comfy

https://civitai.com/models/1340141/squish-effect-wan21-i2v-lora?modelVersionId=1513385

Recommended machine:Ultra-PRO

Workflow Overview

How to use this workflow

Step 1: Load Image

Step 2: Adjust Video parameters

Under 81 frames doesn't seem to work

Step 3: Adjusting Lora weights

Step 4: Input the Prompt

No need to describe the entire picture in detail, just enter key information such as lens, action, etc.

Step 5: Set the number of sampler steps

When I was testing, the effect of generating a two-dimensional video was very good when step=30, and the real person would have a bad face; when step=50, the real person's facial texture gradually became clear. If the effect is not as expected, please try again.

Step 6: Get Video

You can change the video length by setting frame_rate or num_frames (in WanVideo Empty Embeds). Video length = num_frames/frame_rate

Details
APPComfyUI(v0.3.23)
Update Time03/18/2025
File Space367.1 MB
Models1
Extensions4