Simple LLM: Display Text

LLM nodes in ComfyUI have a visibility problem: they produce strings, and strings are invisible. Run a prompt and all you get is a wire and a shrug. Simple LLM: Display Text is the node that fixes the "what actually came back" problem - you feed it any string and it shows the contents in the UI and the console, right there in your workflow.

It's part of the SimpleLLM family in ComfyUI-NS-Util (NakamuraShippo's utility pack, the LLM section of which the README marks as still in testing). Think of it as the text equivalent of an image preview node - a debug window you park at the end of a chain. It's the first thing to reach for when you're trying to figure out whether your prompt pipeline is producing what you think it is.

How it works

The node takes a text string and does three things: prints a formatted block to the ComfyUI console (previewing the first 500 characters and noting the total length if it's longer), pushes the full text to the UI so it appears on the node, and passes the text straight through. That pass-through is the useful bit - Display Text is also an output node, meaning it terminates the graph branch, but it still emits the string on the other side so you can keep using it further down.

The inputs that matter

• text - the string to display. It's forceInput, so it's meant to be wired in from a node output (like Simple LLM Run: Prompt's response) rather than typed in place. The input must come from another node.

Output: text - an exact passthrough of what you fed in, handy if you want to both display and continue the chain.

Installing the pack

# ComfyUI Manager → Install via Git URL:
https://github.com/NakamuraShippo/ComfyUI-NS-Util

# or:
cd ComfyUI/custom_nodes
git clone https://github.com/NakamuraShippo/ComfyUI-NS-Util
pip install pyyaml watchdog

Restart ComfyUI. No model downloads, no network, no heavy deps - this is a pure UI/console node.

Common issues

The classic confusion is wiring order: because text is forceInput, you can't just type into it - you must connect the node that produces the string. If the node shows nothing, check that the upstream actually ran. If your text is long and you see a truncated preview in the console, that's by design (500-char preview); the UI widget shows the full text. One more note: this node overlaps with Simple LLM: String Viewer, which adds prefix/suffix wrapping - pick the one that fits; no need for both.