❌[DEPRECATED] Illustration-Style Prompt Encoder

If you've loaded a workflow that references this node and ComfyUI is showing it as deprecated, that's the whole story in one word: don't panic, it still runs, but the author has moved on. Illustration-Style Prompt Encoder was one of the original Z-Image Power Nodes - pick an illustration style, get your prompt rewritten in that style, and encoded into conditioning. It's been superseded by the general-purpose Style & Prompt Encoder (StylePromptEncoder2), which folds illustration styles into a single library of 100+ and adds the searchable gallery. The ❌ in the menu is a signpost, not a breaker.

What it does

The workflow shape is identical to the current encoder: you feed it a CLIP model, your text prompt, and a style_to_apply chosen from the illustration style set. It rewrites the prompt to match the style, then tokenizes and encodes it through the CLIP to produce CONDITIONING for your sampler. It also passes back the styled prompt as a STRING so you can see (or log) what actually got encoded.

There's one extra input the current stable node still has: customization, a multiline string where you can override or add styles using the same >>> block format with {$@} as the prompt placeholder. If you've built a customization library around this node, that muscle memory carries straight over to the replacement.

Inputs & outputs

• clip (CLIP) - the text encoder, i.e. Z-Image's Qwen3-4B.
• style_to_apply (COMBO) - the illustration style.
• text (STRING, multiline) - your base prompt.
• customization (optional STRING) - custom style definitions.
• Outputs: CONDITIONING + STRING (styled prompt).

Install

Same pack as everything else here:

cd ComfyUI/custom_nodes
git clone https://github.com/martin-rizzo/ComfyUI-ZImagePowerNodes

Restart ComfyUI (or install via ComfyUI Manager, search "Z-Image Power Nodes"). No extra pip dependencies.

Should you use it?

Only if a saved workflow forces you to. The node works, but "deprecated" here is the author flagging that it's frozen while the stable encoder keeps evolving - the current Style & Prompt Encoder gives you the same illustration styles plus photo, wild, and custom ones, a gallery for browsing them visually, and it's where new styles land. Old workflows referencing this node are the classic "it renders, but you're on yesterday's road." If you have one, swap in StylePromptEncoder2, re-pick your style from the unified list, and move on. If you're starting new, don't reach for this node at all.