Nodes/ComfyUI-ZImagePowerNodes/❌[DEPRECATED] Photo-Style Prompt Encoder
ComfyUI Node

❌[DEPRECATED] Photo-Style Prompt Encoder

The deprecated photo-style encoder — your saved workflows still open, that's about it

By martin-rizzo·Created 8 months ago·Updated 7 days ago· 357
❌[DEPRECATED] Photo-Style Prompt Encoder
  • clip
  • CONDITIONING
  • STRING
style_to_apply
text
customization

Photo-Style Prompt Encoder was the original "make my Z-Image output look like a specific kind of photograph" node in this pack: pick a photographic style, get your prompt rewritten in that style's language, and encoded into conditioning. It's now marked deprecated, and the story is the same as the other deprecated nodes here - it works, it's frozen, and the current Style & Prompt Encoder (StylePromptEncoder2) absorbed its job into a single 100+ style library with a searchable gallery.

If a workflow you downloaded references this node, ComfyUI will still execute it. The ❌ tag means "the author moved on," not "this is broken."

What it does

The flow mirrors the current encoder exactly: clip in, text in, a style_to_apply selected from the photographic style set, and the node applies the style template to your prompt before tokenizing and encoding it through the CLIP. Outputs are CONDITIONING (for your sampler) plus the styled prompt as a STRING, so you can see what got encoded.

It also keeps the customization input - the multiline string where you define or override styles using the >>> block format with {$@} as the prompt placeholder. If you built a personal photo-style library in this node, that format carried over unchanged to the current encoder, so your definitions aren't wasted.

Inputs & outputs

  • clip (CLIP) - the text encoder (Qwen3-4B for Z-Image).
  • style_to_apply (COMBO) - the photographic style.
  • text (STRING, multiline) - base prompt.
  • customization (optional STRING) - custom style definitions.
  • Outputs: CONDITIONING + STRING.

Install

Part of the Z-Image Power Nodes pack:

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

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

Use it or not?

Only if you're keeping an old workflow alive. The current Style & Prompt Encoder gives you the same photographic styles plus illustration, wild, and custom ones, a visual gallery, and it's where the author keeps shipping new styles - this node gets none of that. When you inevitably touch the old workflow, swap this for StylePromptEncoder2, re-select your style from the merged list, and you'll have lost nothing. Starting fresh? Don't go looking for this one.

Category⚡Z-Image/__deprecated

Inputs (4)

NameTypeDefaultDescription
clipCLIPThe CLIP model used for encoding the text.
style_to_applyCOMBOThe style you want for your image.
textSTRINGThe prompt to encode.
customizationoptSTRINGAn optional multi-line string to customize existing styles. Each style definition must start with ">>>" followed by the style name, and then include its description on the next lines. The description should incorporate "{$@}" where the main text prompt will be inserted.

Outputs (2)

NameTypeDescription
CONDITIONINGCONDITIONINGThe encoded text used to guide the image generation.
STRINGSTRINGThe prompt after applying the selected photographic style.