CLIP Text Encode (Prompt)
Tokenizes positive and negative text prompts, supporting (word:1.2) attention weights and embedding: tags. Package: Built-in Core.
Updated Oct 17, 2026 · 1 min read
- Node / Pack
- CLIP Text Encode (Prompt)
- Category
- conditioning
- Inputs
- clip, text
- Outputs
- CONDITIONING
- Source Pack
- Built-in Core
What CLIP Text Encode (Prompt) does in a ComfyUI graph
Tokenizes positive and negative text prompts, supporting (word:1.2) attention weights and embedding: tags.
On the canvas, this node accepts `clip, text` and emits `CONDITIONING`. Every pin is color-coded by data type so you cannot accidentally wire a pixel `IMAGE` tensor into a `LATENT` pin without an intermediate encode step.
Installation and missing-node recovery on Windows
CLIP Text Encode (Prompt) ships inside the default ComfyUI core on Windows. Double-click anywhere on the empty Studio canvas and type its name to drop it into your graph.
Download the full Windows desktop or portable package at /download to get started with a clean Python 3.12 environment.
FAQs
How do I fix "CLIP Text Encode (Prompt)" showing up as a red box in ComfyUI?
Update your ComfyUI installation to the latest build from /download so all recent core nodes are registered.
What are the main inputs and outputs of CLIP Text Encode (Prompt)?
Inputs: clip, text. Outputs: CONDITIONING.
Run on your hardware. Free forever.
The full ComfyUI engine: open source, fast, extensible, and yours to run however you want. Download the desktop app and open this workflow on your own machine.
