DCAU Style for Pony XL (DC Animated, Justice League/Unlimited)

This Lora only works on Pony v6 XL and Pony-based models.Trained on 128 images, almost all screenshots from Justice League/Unlimited and other DCAU shows with the Bruce Timm streamlined animated series designs.PromptingTrigger word: dcaustyleStrength: 0.9 - 1.0Recommended prompting:Use Pony's quality tags: score_9, score_8_up, score_7_up, etc.Use booru tags. Some natural language prompting might work too.NotesNotes on version 1: This is my first try at training a style lora. Let me know how it works, because I don't know how flexible it is. Mostly trained on "1girl, solo" type images. Anatomy may not be very coherent with complex multi character images. This was trained on civitai because I don't have enough vram.It was made with 128 images, almost all screenshots from fancaps.net of JL/U, TNBA, and DCAU movies with the Timmverse art style. I picked images that had clear poses and tried to avoid overtraining on any one character or background. More emphasis on named female characters, but I included some random characters and scenery. I avoided crowd shots or pictures where characters were overlapping, since that seemed to confuse the AI based on a previous attempt. There were also just 2 to 3 generated nsfw images, which was an experiment I might expand on in the future. Nonetheless, it can do nsfw, since this is Pony after all.Many of the frames from the cartoon are simple and at times "badly drawn". I wanted it to look authentic to the cartoon, not refined, detailed artwork. However, maybe it was a bad idea to train this on "bad" drawings... (Somebody else made a lora that looks more like Bruce Timm's personal artwork: Retro Cartoons, the Animated Series.)If you know how this dataset can be improved, please give me some advice. I plan to make an upgraded version.CharactersThis is meant to be a style lora, but I also tried to make it like a multi-character lora, which maybe was a mistake in trying too much. Some female characters were trained with 5 - 10 images each, and can be generated with medium to low accuracy. (Other people are already making individual JLU character loras for Pony, which should work with this.) Try using the name and at least some of booru tags used to train them:Batgirl: batgirl, barbara gordon, blue eyes, mask, red hair, long hair, black lips, small breasts, two-tone cape, belt, black bodysuit, yellow gloves, bootsBlack Canary: black canary, blue eyes, blonde hair, long hair, sidelocks, medium breasts, cropped jacket, black leotard, pantyhose, cleavageGalatea: galatea /(power girl/), blonde hair, bob cut, swept bangs, aqua eyes, medium breasts, belt, white leotard, highleg leotard, long sleeves, cleavage cutout, glovesHawkgirl (Justice League outfit, mask doesn't always work): hawkgirl, hgmasked, feathered wings, orange hair, long hair, medium breasts, earrings, strapless, leotard, belt, tights, red footwearHawkgirl (JLU outfit with no mask): shayera hol, feathered wings, green eyes, orange hair, parted bangs, long hair, medium breasts, yellow sports bra, yellow track pants, midriff, navelHuntress: huntress /(dc/), helena bertinelli, black hair, long hair, black eyes, medium breasts, mask, cape, black leotard, navel cutout, utility belt, elbow gloves, thigh boots, thigh holsterSupergirl: supergirl, blonde hair, swept bangs, blue eyes, headband, medium breasts, white shirt, crop top, midriff, cape, miniskirt, glovesWonder Woman: wonder woman, lasso, black hair, long hair, blue eyes, red lips, tiara, star earrings, star /(symbol/), strapless, leotard, high heel boots, red footwearVixen: vixen /(dc/), very short hair, pixie cut, black hair, medium breasts, dark-skinned female, orange bodysuit, cleavage, plunging neckline, tooth necklace, dangle earrings, belt, elbow gloves, high heels, clawsZatanna: zatanna zatara, blue eyes, black hair, long hair, medium breasts, magician, formal, tuxedo, suit jacket, bowtie, vest, leotard, pantyhose, sleeve cuffs, top hat, high heelsTry "gotham city, red sky, dark, night, shadow" to get that Gotham City look.Other characters represented by 2 or 3 pictures in the dataset: Circe, Giganta, Katma Tui, Lois Lane, Poison Ivy, Harley Quinn (jester costume and non-costumed as "harleen quinzel") etc. Prompting these might work somewhat, but not accurately. Many characters are missing and named male characters were not strongly trained. Maybe next time.