Translate Text to Chinese 🐼

What it is

A small, single-purpose utility: feed it text, get the Chinese translation back. It sits in the pack's "tools" category rather than the image2prompt category proper, and it's there for a plain reason - this pack was built by and for a Chinese-speaking ComfyUI audience. The README ships a full Chinese section before the English one, and Text2Prompt's own system-prompt presets include options like "you're skilled at translating Chinese to English" and "you're skilled at translating classical Chinese to English." Translate to Chinese is the other direction of that same instinct: if a chain of nodes upstream (a captioner, a prompt rewriter, an English LLM output) hands you English text, this node lets you read it in Chinese without leaving the graph.

How it works

It's a text-in, text-out translation call - you give it a string, it gives you back the Chinese version. There's nothing to configure about the translation itself beyond the source text; the only real controls are around caching and logging.

Inputs and outputs

• text - multiline string, the text to translate.
• cache - enabled by default. Re-running the same text won't re-trigger a fresh translation call; it reuses the cached result. Worth knowing if you're iterating on a workflow and expecting a translation to update after you've changed the upstream node but kept the same literal string flowing into this one - check whether cache is masking a stale result before you assume something's broken.
• print_output - enabled by default, echoes the translated string to the console. Turn it off once you've confirmed it's working and don't need the log noise.

Single STRING output, not a list - one input string in, one translated string out.

Installing it

This node ships inside the same pack as everything else here. Via ComfyUI Manager, search "Comfyui_image2prompt." Manually:

cd ComfyUI/custom_nodes
git clone https://github.com/zhongpei/Comfyui_image2prompt

Restart ComfyUI afterward. Note that the README's own clone command is actually typo'd - it points at a hyphenated repo name (Comfyui-image2prompt) that 404s; use the underscored URL above.

Unlike the captioning and prompt-generation nodes in this pack, there's no model file to download for this one - it doesn't show up in the README's model list, and the schema takes no model input, so there's nothing extra to fetch before it works.

Common issues

There's genuinely not much to go wrong here - it's the simplest node in the pack. The one thing worth flagging is generic to the whole pack rather than specific to this node: it's installed into the same Python environment as every other custom node you have, so if Comfyui_image2prompt's dependencies conflict with something else you've got installed, you'll see it as an import failure at ComfyUI startup rather than a runtime error on this specific node. If the node doesn't show up in your node list at all, check the ComfyUI console log on startup for an import error tied to this pack before assuming the node itself is broken.

If you only need this one node and don't care about captioning or prompt generation, it's still worth pulling the whole pack rather than trying to extract just this file - the nodes aren't designed to be split out individually.