Character Video Generation (AnimateLCM, OpenPose Controlnet, Lora, Face Detailer)

Introduction

This workflow is based on the work by Jerry Davos, with modification. This workflow features:

1. Video generation using AnimateLCM, uses OpenPose controlnet for the pose of the character and a Lora for the flame animation.

2. Adding details to the face using GroundingDino and Segment Anything to get a mask of the character's face for the 2nd Pass KSampler.

3. Sharpening and Frame Interpolation as post processing.

Custom Nodes Needed

Recommend to install using ComfyUI Manager (https://github.com/ltdrdata/ComfyUI-Manager)

1. AnimateDiff Evolved

2. Advanced Auxilliary Preprocessors

3. Video Helper Suite

4. Advanced Controlnet

5. ImpactPack

6. Segment Anything

7. KJ Nodes

8. Essentials

9. Frame Interpolation

10. MaraScott Nodes

Instructions

The 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.