Files
ausboss-ComfyUI-AusBoss/js/docs/AUSBOSS_NODES_ShowText.md
ausboss 05038baaa3 Five basics the normal nodes have: sums, any wire into Show Text, name tokens, word weights, Image Size's numbers
Found in a sweep of the pack against ComfyUI's own nodes: things the normal
node does that the pack's node did not.

- Every number box takes a sum. Click a number, type 1024*1.5 or
  (1920-64)/2 and press Enter, as in ComfyUI's own number boxes: + - * / %,
  brackets and a sign. The reader is the pack's own (sumValue in
  js/shared/scrub_input.mjs) and is only asked when the text is not a plain
  number.
- Show Text takes any wire. Its input was STRING only. A number, an on/off
  value or a list is shown too; a picture or a latent is shown by its size.
  The output stays STRING and carries the text that is shown, so text
  passes through unchanged and a number comes out as text.
- Save Image takes name tokens in the file name, as ComfyUI's own Save
  Image does: %date:yyyy-MM-dd% and %Node.setting% are filled in the
  browser when a run is sent (js/shared/name_tokens.mjs, now shared with
  Save Video), %width% %height% and the time tokens on the server. The
  path preview shows them. A linked filename is never read for tokens.
- Ctrl + Up and Ctrl + Down change a word's weight in the pack's prompt
  boxes (Text, Krea 2 Encode). The card's text box stopped the key before
  ComfyUI's own listener saw it; those two keys now go on from a multiline
  box, and from nowhere else.
- Image Size shows what it measured beside its outputs after a run
  ("width: 1024"). The numbers go into the output labels, so the node keeps
  its size. ComfyUI says nothing about a node whose answer came from its
  cache, so the numbers are kept in the node's properties and come back
  when a workflow is opened again; a changed picture wire clears them.

No input was added, renamed or reordered. Help pages, README lines, tests
and CHANGELOG entries are included.
2026-10-11 17:10:52 -05:00

1.5 KiB

Show Text

Shows what arrives on a wire, on the node itself: a prompt, an LLM reply, a file name, a number. Wire it to anything you want to read while a workflow runs.

Text passes through unchanged, so the node can sit in the middle of a wire instead of at a dead end.

Controls

  • text: What to show. It takes any wire: text, a whole number, a number with decimals, an on/off value, a list.

Output

  • text: The text that is shown. Text that came in is passed on untouched. A number comes out as text (1024), so this node also turns a number into text for a node that wants text.

Panel

The panel fills the node, so drag the node taller to read more at once. The text can be selected and copied straight off the node, and ⧉ in the corner copies all of it; empty panel space still drags the node and the wheel still zooms the graph.

The last shown text is saved with the workflow, so a reloaded graph reopens showing its previous result. Very long text is cut off in the display (with a note saying so). The output wire always carries all of it.

Technical details

  • A list or a dictionary is shown as JSON.
  • A picture, a mask or a latent is shown by its size, such as tensor 1 x 1024 x 768 x 3, float32, because its numbers would fill the panel. Use Image Size 🆎 to get a picture's width and height as numbers.
  • A node that hands out a list of values runs Show Text once per value, and the panel shows one line for each.
  • Anything else is shown as Python prints it.
  • The node performs no network requests.