Question 1

What is ComfyUI?

Accepted Answer

ComfyUI is a node-graph interface for Stable Diffusion — instead of a fixed form, you (or the tool, in this case) wire together nodes like checkpoint loaders, samplers, and encoders into a custom pipeline. RnR Vibe runs a hardcoded SD 1.5 text-to-image workflow through it as a second, independent local image backend.

Question 2

How is this different from the AI Image Generator?

Accepted Answer

The AI Image Generator uses AUTOMATIC1111 (A1111) WebUI. This tool uses a completely separate ComfyUI server. Both run locally on the same GPU and can load the same Stable Diffusion 1.5 checkpoints, but they're independent backends with their own strengths — ComfyUI's execution engine is generally faster for repeated runs since it caches unchanged parts of the graph.

Question 3

Why can I only run one at a time?

Accepted Answer

Both ComfyUI and Stable Diffusion WebUI need the same 6 GB GPU. Running both simultaneously risks running out of VRAM. The start scripts detect a conflicting service and offer to stop it automatically before starting the other.

Question 4

Do the two backends share the same models?

Accepted Answer

Yes. ComfyUI is configured with an extra_model_paths.yaml pointing at the A1111 install directory, so every SD 1.5 checkpoint already downloaded for the AI Image Generator shows up in this tool too — no duplicate multi-gigabyte downloads.

Question 5

Do I need a GPU to use this?

Accepted Answer

RnR Vibe runs ComfyUI on the host machine's GPU via Cloudflare Tunnel. You only need a browser — no local install, no API key.

ComfyUI Image Generator

Select Checkpoint