nuvoize/comfyui-brkn-prompt-randomizer — explained in plain English
Analysis updated 2026-05-18
Browse and select a base prompt pack plus wardrobe, lighting, and location modifier packs visually before generating an image.
Generate varied but controlled prompt text from reusable prompt packs using seeded randomization.
Lock certain prompt choices in place while rerolling others for new variations.
Organize large prompt libraries into categorized, thumbnail-previewed packs instead of raw text files.
| nuvoize/comfyui-brkn-prompt-randomizer | aim-uofa/reasonmatch | airbone42/360-data-athlete | |
|---|---|---|---|
| Stars | 12 | 12 | 12 |
| Language | Python | Python | Python |
| Setup difficulty | moderate | hard | hard |
| Complexity | 3/5 | 5/5 | 4/5 |
| Audience | developer | researcher | general |
Figures from each repo's GitHub metadata at analysis time.
Requires an existing ComfyUI installation and manually copying the folder into the custom_nodes directory.
BRKN Prompt Randomizer is an add-on for ComfyUI, a node based tool people use to build AI image generation workflows. This add-on adds two custom nodes that work together to build varied text prompts for image generation out of reusable, organized packs of prompt material, such as wardrobe choices, makeup, lighting styles, camera styles, locations, actions, and transportation. The first node is a visual pack browser and selector. It shows the user available prompt packs with thumbnail images so they can pick, before generating anything, one base pack plus any number of additional modifier packs grouped into categories like base packs, camera style and lighting, wardrobe and makeup, locations, transportation, and actions. It supports searching through packs and remembers the user's selections inside the saved workflow file. The second node is the actual prompt composer, which takes the browser's selection and builds the final prompt text. It applies filtering, exclusion rules, pinned entries that should always be included, compatibility rules between packs, randomization based on a seed, locking specific choices in place, and the ability to reroll for a new variation. Each pack's thumbnails are defined through metadata files that point to image assets, typically square WebP images, with some pack types showing two images, such as a wider shot as the main thumbnail and a close-up as a preview. If a thumbnail image is missing, the browser shows a warning and falls back to a placeholder tile rather than breaking the workflow entirely. The README is explicit that the packs themselves only provide prompt text and trigger words, not any bundled LoRA model files, meaning which LoRA models to use alongside the generated prompts remains a separate choice made elsewhere in the user's own ComfyUI workflow. To install it, the project folder is copied or cloned into ComfyUI's custom nodes directory, after which ComfyUI needs to be restarted and the browser page refreshed for the new nodes to appear.
A ComfyUI add-on with two custom nodes for browsing modular prompt packs and composing varied, controlled AI image generation prompts from them.
Mainly Python. The stack also includes Python, ComfyUI.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.