ZML_多文本输入_五V2

Here's the thing that makes ZML_MultiTextInput5V2 different from its siblings: it doesn't merge first and ask questions later. Five inputs, and you get five individual outputs back, plus a merged string and a list on the side. The "V2" is the pack's answer to a specific need - the README says flat out it was made for the pack's 文本图像 (text-image) node, which wants each text line separately so it can render each one as its own row.

So while ZML_MultiTextInput3 and 5 are prompt-builders (boxes in, one string out), this one is more of a distributor: five values in, five values out, and the merge is just a bonus. If you need to feed five different strings to five different places, or you want to keep the pieces alive downstream instead of losing them inside a joined blob, this is the node.

What's on it

Inputs (all single-line, not multiline - that's another deliberate difference):

• 分隔符 (default ,\n\n) - used only for the merged output.
• 文本1_输入 through 文本5_输入 - five single-line boxes.

Outputs:

• 文本1 through 文本5 - the five inputs echoed through unchanged, each on its own port.
• 合并文本 - the join of all non-empty inputs with your separator.
• 文本列表 - the same values as a list, no separator. That's the OUTPUT_IS_LIST port for the pack's list-iteration machinery.

When it earns its keep

• Text-image annotation. Render five caption rows onto an image - the exact use the README names.
• Fan-out. One node feeds five downstream consumers with five distinct strings, keeping them distinct.
• Batch hand-off. Emit the list output to a list-iterating node while still having the merged string for something else.

The single-line inputs are worth remembering: if you paste a big multiline prompt in here it won't behave like the 3/5 siblings. This node assumes short values per slot.

Install

Standard pack install:

cd ComfyUI/custom_nodes
git clone https://github.com/zml-w/ComfyUI-ZML-Image
# restart ComfyUI

or ComfyUI Manager → search "ComfyUI-ZML-Image". No dependencies beyond the pack baseline. Chinese-first UI - 分隔符 is "separator," 合并文本 is "merged text" - translation patch at https://github.com/zml-w/ZZZ_ZML_English_Patch.

Note this one doesn't have the 格式化标点符号 switch that the 3/5 variants carry - the V2 merge skips the punctuation cleanup. If you're using the merged output and want the tidy-up, run the result through a formatting node or pick ZML_MultiTextInput5 instead. That's a genuine behavioral difference, not a bug.