What you'll learn
✓ Design end-to-end ComfyUI workflows for text-to-image, image-to-video, and reference-driven generation.
✓ Build repeatable creative pipelines using nodes, templates, workflow saving/export, and canvas navigation.
✓ Create image-to-video results with Kling O1, using reference images to guide motion, identity, and consistency.
✓ Generate high-quality text-to-image outputs with Ideogram v3, using prompt engineering, prompt order, and magic prompt strategically.
✓ Run large text-to-image pipelines in Comfy Cloud using Qwen Image models to improve Performance over local Installation
✓ Modify complex workflows by unpacking subgraphs, bypassing nodes, and tracing KSampler, CLIP, and latent flows.

Requirements
● A Comfy Cloud subscription (ESSENTIAL)
● An up-to-date AI accelerator with at least 16GB VRAM: NVIDIA RTX is preferred but Apple Silicon or AMD ROCm can be also used.
● (OPTIONAL for local workflows) - A machine with at least 128 GB RAM or 128 GB unified memory