This workflow is currently available for free beta testing on our platform at www.giz.ai/ai-face-video. This workflow integrates the power of the AnimateLCM model with FaceID and ELLA to create dynamic, realistic face animations directly from text prompts and images.

Key Features

• AnimateDiff and AnimateLCM enable fast video creation even on low VRAM (8 seconds on RTX 4070 Ti Super with 16GB VRAM)
• Integrated ELLA to improve prompt adherence and animation consistency.
• Supports video upscaling and frame interpolation.
• The IPAdapter FaceID Plus v2 can be integrated to apply facial images.

If you have any questions or issues, please file an issue in the following repositories.

https://github.com/GizAI/ComfyUI-workflows

by GizAI Team