Prompt Styler Sports

SDXLPromptbySportsArt is the sports-themed node in wolfden's SDXL Prompt Styler pack. It ships ~31 presets built around athletic moments - Olympic Triumph, Basketball Slam Dunk, Surfing the Perfect Wave, Motorsport Grand Prix, Winter Olympics Figure Skating, Martial Arts Mastery, and more. Type your subject, pick a sport, and the node wraps it in that action's scene.

It's a shortcut to energy and motion - the stuff that's fiddly to prompt by hand. Each preset is a full scene rather than a single keyword, so it's great for quick dynamic images and less great when you want tight control over the exact frame.

How it works

Each sports style is a JSON entry with a {prompt} placeholder in its prompt field and a negative_prompt. Pick "Basketball Slam Dunk" and your text_positive slots into a template full of arena, motion, and action language. No model, no API, no key - string substitution against a lookup table. The dynamism comes from the keywords the preset injects around your subject.

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

The inputs that matter

• text_positive - your subject. The preset brings the action.
• style - the sport, ~31 options.
• text_negative - optional, merged with the preset's negative.

log_prompt (No/Yes) prints the finished prompt to the console. 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 the same string can go 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 look under the Style Prompts submenu. No downloads, no dependencies.

Where people get tripped up

Action scenes are where SDXL's anatomy weaknesses show up most - mid-motion limbs, hands gripping equipment, crowds of small background figures. That's the base model's limitation, not the styler's; the preset asks for the dynamic pose, and the model does its best. Expect to cherry-pick seeds, and consider an ADetailer-style face/hand fix pass if you're going for polish.

Because each preset is a whole scene, your subject can get swept into the preset's sport whether or not it fits. If the mix is off, flip log_prompt to Yes, read what got built, and trim. The styles are JSON in the pack folder.

Pack-wide caveat: these templates were tuned for SDXL and its CLIP encoder, so they're strongest 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. If the node doesn't appear after install, restart fully and check Style Prompts, not the root menu.