Clothing_State Styler

Clothing_StateStyler is a small, focused menu: ~49 tags describing the state of clothing rather than the garment itself - open clothes, unbuttoned, unzipped, see-through, clothing aside, undressing. It's a sibling to the other "state" nodes in this pack, and it exists so you can dial the degree of dress from a dropdown instead of typing booru tags by hand. Straightforward tool, clearly aimed at NSFW and suggestive work; described plainly here because that's what it is.

As with every anatomy/state node in the pack, the key fact is that these are Danbooru tags, and they only land on models trained on Danbooru-tagged data - the anime/NSFW SDXL finetunes (Pony, Illustrious, NoobAI, WAI) and the SD1.5 anime lineage. On a photoreal checkpoint or SDXL base, most of these tags do nothing, because the model never learned them. The dropdown doesn't check; it just injects.

How it works

MileHighStyler is a fork of the classic SDXL Prompt Styler. Each menu entry is a JSON template with a {prompt} slot; Clothing_StateStyler drops your text_positive into the chosen tag's template and wraps the style text at a strong default weight (~2.0, per the pack docs). Output is text, into your CLIP Text Encode - the node rewrites your prompt and touches nothing else.

The inputs and outputs that matter

• clothing_state - the ~49-entry tag dropdown. none is the off switch.
• text_positive - your subject and scene; it lands in the template.
• text_negative - optional negative text.

log_prompt prints the finished prompt to the console so you can see the exact tag and weight it added. Outputs are text_positive and text_negative strings, into a CLIP Text Encode.

Installing it

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

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

then restart. No models, no requirements.txt, no dependencies - Python and JSON. Nodes appear under ali1234/stylers.

Where people get burned

• Wrong checkpoint. Booru tags need a booru-trained model. Match this to Pony/Illustrious/NoobAI/WAI and it works; on photoreal or base SDXL it's mostly inert.
• Model era. The 2.0 weighting is CLIP-encoder syntax, discarded on the 2026 LLM-encoded models (Flux 2, Z-Image, Qwen). Even where an LLM-encoded booru model knows the tag, it ignores the weight - so write the tag plainly there. This node is happiest on the SDXL/SD1.5 CLIP family.
• State tags fight the garment. If your prompt also specifies a fully-described outfit, a strong "state" tag may contradict it and you'll get muddle. Keep the two consistent, and don't over-weight.
• CFG 1. Any carried negative only does something above CFG 1 - nothing on a Turbo/Lightning CFG-1 setup.