KREA 2

Lack of examples (for for the Not Red Civitai) due to Civitai automatically declaring her outfit is rated R so all of the examples listed with the exception of 2 images at the time of posting this are rated R to XXX

Description

How to use

Use the trigger s0rc3r3ss.

For best results, prompt the form you want explicitly:

• Sorceress form: s0rc3r3ss in her sorceress form, wearing the falcon outfit

• Human form: s0rc3r3ss in her human form, wearing the purple outfit

For stronger fidelity, include key visual anchors such as long white hair, falcon headpiece, white feathered leotard, blue sleeves, orange feathered wings for Sorceress form, or red ponytail and purple outfit for human form.

For the trained visual style, add:

1980s hand-drawn cartoon animation cel style with flat colors and bold dark outlines

It works best when you describe pose, camera angle, environment, and action clearly, then let the LoRA handle the character identity.

Sorceress for Anima

A character LoRA for Sorceress trained on her classic cartoon appearance using Anima base. This model focuses on her main falcon outfit, her alternate purple outfit, and Castle Grayskull as a trained location element.

The main outfit is her iconic falcon look with white hair, falcon mask, orange and white headpiece, blue sleeves, white feathered one piece, large orange feathered wings, blue boots, and white fur boot cuffs. The alternate outfit features red hair in a ponytail, a purple sleeveless mini dress, black belt, yellow armbands, yellow wrist cuffs, purple boots, and fur boot cuffs.

Trigger

s0rc3r3ss

Main Falcon Outfit Tags

s0rc3r3ss, 1girl, solo, white hair, long hair, red lips, falcon mask, orange headpiece, white headpiece, blue sleeves, blue collar, white feathered one piece, white one piece bathing suit, large orange feathered wings, blue boots, white fur boot cuffs, falcon

Useful pose tags:

full body, upper body, close up, front view, side view, wings spread, arms raised, arms outstretched, open hands, wide stance, looking at viewer

Purple Outfit Tags

s0rc3r3ss, 1girl, solo, red hair, ponytail, purple sleeveless mini dress, black belt, yellow armbands, yellow wrist cuffs, purple boots, fur boot cuffs

Useful pose tags:

full body, cowboy shot, front view, side view, standing, crawling, on hands and knees, arms raised, one leg lifted, open mouth, looking at viewer

Example Prompt

masterpiece, best quality, amazing quality, very aesthetic, absurdres, s0rc3r3ss, 1girl, solo, full body, front view, white hair, long hair, red lips, falcon mask, orange headpiece, white headpiece, blue sleeves, blue collar, white feathered one piece, white one piece bathing suit, large orange feathered wings, blue boots, white fur boot cuffs, falcon, wings spread, arms outstretched, open hands, wide stance

Notes

Use white one piece or white feathered one piece for her main outfit. Avoid prompting “bodysuit” unless you specifically want the model to drift into a full coverage suit.

For best results, keep the outfit tags grouped together and place s0rc3r3ss near the start of the prompt.

UPDATE 02/11/2026 ZIT V2

It helps to specify characteristics like "orange wings" "white one piece body suit" "orange and blue birdlike helmet" "white hair" "blue boots" if you want the traditional look.

V2 is captioned differently. works really well across all mediums

UPDATE 12/4/2025

Sorceress Z Image Turbo

TRIGGER WORD: S0rceress

For Z Image Turbo version, use trigger S0rceress

My first Z Image Turbo LoRa that I feel is good enough to share. Lora strengths around .6-.85 are best.

TRIGGER WORD: S04cer3ss

This is a tribute to my first crush, Sorceress of Castle Grayskull

A few observations and notes:

I made this Lora twice.

I trained the first lora on the same data set with a combination of Joy Captioning and my own captioning. Then I did a second Lora with no captions. Just a trigger word.

After going through both, I ended up going with the no captions Lora although I don't think that's always going to be the right choice. Mainly my choice for going with the no captions was that I trained the Lora on as much of a diverse set of media types and fan's interpretations as I could find and the no caption Lora felt like it had more artistic freedom to push the boundaries whereas the captioned images required more precise prompting. Somewhat hard to explain but I suggest people that play with making Loras try out both. See what works best. It's not a one size fits all for all Loras at least in my opinion.

Something else I noticed, despite specifically training on non ai images that had good hands and feet and no signatures or watermarks, somehow they still found their way in. Perhaps thats just the impact Loras have on it until the technology gets better.

Lastly. Most images were made on ComfyUi however I did make some on Forge so people could see the prompts that were used. I used the full Dev model for the images. It was by far the most vibrant and detailed model. If you try running this on a "realistic" flux model, I found the outputs were extremely plain and dull. I do not suggest it.