Sign In

Horror Dreamcore Flux.1 - V1 Showcase

Loading Images

Flux.1 Version — Tagging System Summary

This LoRA was trained with a modular, atomic tagging structure designed for flexible prompt-building rather than fixed per-image descriptions.

Trigger word: horror_dreamcore

Shared vocabulary reference (identical wording wherever a feature repeats):

  • Helmets: full-face helmetbubble helmetdome helmetchrome visor helmettinted visorgoggles

  • Materials: wet-look finishchrome finishlatex texturetranslucent panelworn textureweathered texturesplatter texturemesh textureiridescent finish

  • Structure: bodysuitarmor platingrobetrench coatcargo pantshooded robe

  • Features: exposed midriffexposed organsexposed muscleexposed ribstentacle growthsmushroom growthscrystal growthsfoliage embeddedvine circuitryglowing veinsglowing orbsglowing accent dotstube wiringmechanical joints

  • Armor parts: shoulder pauldronchest platechest window panelhip armorknee armorankle armorgauntletsbootssandalsbackpack devicesatchel pouchutility beltstrap harness

Tagging approach:

  • Every caption uses short, isolated natural-language phrases (materials, colors, structure, and features each get their own tag rather than being fused together).

  • Repeated concepts use identical wording across the entire dataset (e.g. "dome helmet" always means the same silhouette, never swapped with "bubble helmet" or "glass dome" for the same feature) so the model reinforces one strong concept instead of several weak ones.

  • Constant elements shared across the whole dataset (multi-view sheets, studio backdrops, standing poses) were deliberately pruned from every caption. These traits are absorbed directly into the trigger word, so horror_dreamcorealone reproduces that consistent presentation style without needing to spell it out in your prompt.

What this means for prompting:

  • Call horror_dreamcore for the baseline dreamcore-horror armor/character aesthetic.

  • Add modular descriptor tags (helmet type, material, color, mutation/growth feature, armor part) to pull specific traits from different trained designs and recombine them into new characters.

  • Keep tag stacks short (4–6 modular tags after the trigger) for the cleanest results — over-stacking conflicting structure tags (e.g. two competing garment types) will fight each other in generation.

Comments