<h3 id="updated-wan2.2">UPDATED WAN2.2</h3>CrashZoom-Wan2.2-I2V-A14B.You can use MediaInfo to check the generation info in the video. The workflow I used ComfyUI-WanVideoWrapper. If you like my job , you can donate me here: <a target="_blank" rel="ugc" href="https://ko-fi.com/ghostshell">https://ko-fi.com/ghostshell</a>. Just paying the electricity bill costs me 1,000 yuan a month...This LoRA is not for commercial use. Please lease dm me, If you have any business cooperation inquiries.This LoRA is trained for Wan2.2-high noise. Please make sure add it to the high noise Wan2.2 model.Suggest LoRA Strength:0.7-0.9. Prompt suggestion(It is trained on live-action movie,please add anime style if you using on anime):rapid zoom in effect,zoom in on face<h3 id="wan2.1">WAN2.1</h3>CrashZoom-Wan2.1-I2V-720P.You can use <a target="_blank" rel="ugc" href="https://mediaarea.net/en/MediaInfo">MediaInfo</a> to check the generation info in the video. The workflow I used<a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-WanVideoWrapper"> ComfyUI-WanVideoWrapper</a>. I uploaded an article of my experience of training Wan2.1 LoRA (Both I2V &amp; T2V): <a target="_blank" rel="ugc" href="https://civarchive.com/articles/16936/my-personally-training-experience-of-wanstarting-with-data">My Personally Training Experience of WAN:Starting with Data</a>.

Files with SHA256: 8082096eb03a24ba87feed377c73aa9baf5d7a3bb41325067660a1acfd9c3609