What problem does it solve?
This Skill simplifies the process of generating images, video, and audio content using ComfyUI, a powerful tool that leverages the official comfy-cli for setup and execution.
Core Features & Use Cases
- Image Generation: Create custom images using Stable Diffusion, SDXL, Flux, SD3, and other models.
- Video Generation: Produce video content with AnimateDiff, Hunyuan, Wan, and other video generation models.
- Audio Generation: Generate audio content using various audio generation models.
- Use Case: Imagine you want to create a video of a 3D-animated character performing a dance. Use this Skill to generate the necessary frames, combine them into a video, and output the final result.
Quick Start
Generate a video using the AnimateDiff model with the following command:
python3 scripts/run_workflow.py --workflow workflows/animatediff_video.json --args '{"prompt": "a dancing character", "seed": 12345, "steps": 50}' --output-dir ./video_output