Prompt Styler MileHigh

SDXLPromptStylerbyMileHigh is one of the two giant nodes in wolfden's SDXL Prompt Styler pack, sitting just behind the everything-node. It carries ~1,521 style presets spanning art media and movements - 2D Game Art, 3D Animation, Aboriginal Dot Painting, Abstract Expressionism, and on and on. "MileHigh" is just the name of the style collection it draws from. You type a subject, pick a style, and it wraps your text in that look's keywords.

Think of it as a broad style browser: if you want to sample lots of visual styles fast without maintaining your own keyword cheat sheet, this is the node. It overlaps heavily with the everything-node, so if you find yourself wanting cameras or a specific theme too, you may as well use SDXLPromptStylerAll.

How it works

Each style is a JSON entry with a {prompt} placeholder in its prompt field and a matching negative_prompt. Pick "Abstract Expressionism" and your text_positive slots into that template, coming out wrapped in the movement's descriptive keywords. No model, no API, no key - string substitution against a lookup table.

The negative is baked into each preset, and anything you type into text_negative gets merged with it rather than replacing it.

The inputs that matter

• text_positive - your subject, kept short so the style has room to work.
• style - the look, ~1,521 of them. Type to filter or you'll scroll forever.
• text_negative - optional, merged with the preset's negative.

log_prompt (No/Yes) prints the finished prompt to the console - the fastest way to learn what a given style adds. Outputs are positive_prompt_text_g and negative_prompt_text_g, both strings; positive into the CLIP Text Encode feeding your positive conditioning, negative into the negative one. On SDXL you can send the same string into both G and L of a CLIPTextEncodeSDXL.

Installing it

ComfyUI Manager: search SDXL Prompt Styler (wolfden), install, restart. Or manually:

cd ComfyUI/custom_nodes
git clone https://github.com/wolfden/ComfyUi_PromptStylers

Restart ComfyUI and find it under the Style Prompts submenu. No models, no dependencies.

Where people get tripped up

With 1,500 entries, the practical problem is navigation - start typing in the dropdown to filter, don't scroll. And a lot of the more obscure movements in that list are only as good as the base model's knowledge of them; pick something niche and you may get generic output with no error to warn you. When a style flops, that's usually why.

The standard pack caveat applies with force here, since these are style templates: they were built for SDXL and its CLIP encoder, so they help most on SDXL, Illustrious, Pony, NoobAI. On 2026 LLM-encoded models the styling weakens and the inherited negative does nothing at CFG 1, where distilled checkpoints run, because the negative pass isn't computed there. The node styles any model's prompt because it's just text - but it was tuned for SDXL.

If it doesn't appear after install, restart fully and look under Style Prompts rather than the root menu. Turn on log_prompt to see what any style is doing; the presets are JSON in the pack folder and you can edit them.