Clothing_Style Styler (Advanced)

Same 86-entry fabric-pattern menu as the plain Clothing_StyleStyler - argyle, camo, checkered, floral, pinstripe, plaid, polka dot, striped - just in the "Advanced" wrapper that exposes SDXL's two-encoder setup. If you're on SDXL and you want a little more control over how the pattern lands, this is the one. If not, save yourself the extra sockets and use the basic node.

What "Advanced" buys you

SDXL runs two text encoders at once - the big OpenCLIP-G and the smaller CLIP-L. This node splits your positive prompt into text_positive_g and text_positive_l so each encoder can read something different, and adds negative_prompt_to (Both / G only / L only) to route the negative. The honest default is to put the same subject in both and only split if you've got a specific problem to solve. And it's SDXL-only: SD 1.5 has a single encoder, and the 2026 LLM-encoded models (Flux 2, Z-Image, Qwen) don't have this CLIP-G/CLIP-L architecture, so the split there is meaningless.

How it works

It's a fork of SDXL Prompt Styler. Each pattern is a JSON template with a {prompt} slot; your subject drops in, the pattern phrase gets wrapped at a strong weight (~2.0), and rewritten prompt strings come out. Text only - nothing loads a model.

Inputs and outputs that matter

• clothing_style - the 86-entry pattern dropdown. none = off.
• text_positive_g / text_positive_l - your subject, once per SDXL encoder.
• negative_prompt_to - Both (default), G only, or L only.

log_prompt prints the built prompt. The node returns six strings - text_positive_g, text_positive_l, combined text_positive, and the three negatives. Route _g/_l into an SDXL dual CLIP Text Encode, or use the combined text_positive / text_negative like the basic node.

Installing it

ComfyUI Manager: search ComfyUI_MileHighStyler, install, restart. Or:

cd ComfyUI/custom_nodes && git clone https://github.com/TripleHeadedMonkey/ComfyUI_MileHighStyler

No models, no dependencies. Nodes appear under ali1234/stylers.

Where people get burned

• Pattern bleed, still. The Advanced wiring doesn't fix diffusion's habit of smearing "polka dot" across the whole frame. That's a job for lower emphasis or a regional/ControlNet pin, not for the G/L split.
• Splitting for no reason. People assume Advanced = better and start hand-tuning G vs L on a pattern menu. It rarely earns the effort. Same text in both, ship it.
• Off SDXL, the split is dead weight. No G/L encoders means the extra sockets do nothing. Use the plain node - or just type "plaid," which is all this ever produces anyway.