ComfyUI的逐帧可控图生视频方案，输入任意图片，让TA眨个眼！由AnimateDiff配合PIA模型实现
在AnimateDiff中使用PIA（Personalized Image Animator）模型，可以实现可控的图生视频，效果稳定质量高。
在这个视频里，我会演示如何在ComfyUI中使用PIA模型，配合AnimateDiff中的Prompt Travel，实现让输入图片里的小姐姐在指定帧眨眼，并利用IC-Light重打光，规避PIA导致画面明暗度变化的缺陷。
涉及到的插件：
https://github.com/Kosinkadink/ComfyU...
https://github.com/kijai/ComfyUI-IC-L...
模型：https://huggingface.co/Leoxing/PIA/tr...
模型路径： ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved\models
工作流：
https://drive.google.com/file/d/1DOtt...
Watch video ComfyUI的逐帧可控图生视频方案，输入任意图片，让TA眨个眼！由AnimateDiff配合PIA模型实现 online without registration, duration hours minute second in high quality. This video was added by user SweetValberry 20 August 2024, don't forget to share it with your friends and acquaintances, it has been viewed on our site 2,71 once and liked it 8 people.