IntroductionThis workflow is based on the work by Jerry Davos, with modification. This workflow features:<ol><li>Video generation using AnimateLCM, uses OpenPose controlnet for the pose of the character and a Lora for the flame animation. </li><li>Adding details to the face using GroundingDino and Segment Anything to get a mask of the character's face for the 2nd Pass KSampler.</li><li>Sharpening and Frame Interpolation as post processing.</li></ol><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/aJLc6UpWYXs" start="0"></iframe></div>Custom Nodes NeededRecommend to install using ComfyUI Manager (<a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Manager">https://github.com/ltdrdata/ComfyUI-Manager</a>)<ol><li>AnimateDiff Evolved</li><li>Advanced Auxilliary Preprocessors</li><li>Video Helper Suite</li><li>Advanced Controlnet</li><li>ImpactPack</li><li>Segment Anything</li><li>KJ Nodes</li><li>Essentials</li><li>Frame Interpolation</li><li>MaraScott Nodes</li></ol>InstructionsThe instructions on how to use this workflow are included in notes within the workflow. Please feel free to DM me or leave a comment if you have difficulty using this workflow.

Files with SHA256: b600376774e64d6b2042c400a4fa185a1e6a1b3b9b10b8beb2e718603884ac9a