Assumi (World of Warcraft) PonyXL / 1.5 support

PonyXL release for Assumi!

For SD 1.5 settings scroll down.

PonyDiffusion v6 (XL) settings:

Style settings (very important):

score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, uncensored, BREAK

For pure PonyDiffusion v6 XL it is better to use artist style tags or style LoRAs!

For checkpoint mixes like autismmix and mfcg it is not so important.

Use 3D in positive or in negative for 3D arts / anime arts. For 2.5D LoRA don't use 3D in positive. It is very strong tag.

Negative prompt (recommended):

source_pony, source_furry, censored, blurry, head out of frame, watermark, jpeg artifacts, muscular

Also add in negative annoying objects.

Best tags order:

1) score and source_ tags, artist style tags

2) Sentence (for example, "A girl is standing with crossed arms and smiles")

3) tags for concepts, camera, face, body, clothes, background, etc. Order is the same as for 1.5.

Preview images can help.

PonyXL prompt:

Appearance:

Assumi, 1girl,
red hair, short hair, single hair bun, lipstick, makeup, yellow eyes,

optional (without outfit): choker

Sexy warlock outfit:
highleg leotard, spiked shoulder armor, lace trim, fishnet thighhighs, detached fishnet sleeves, stiletto heels

optional:

fishnet cutout, magma belt

small skulls - I don't recommend this tag for skulls because usually they are flying.

Other characters (for interactions):

orc, green skin, interspecies

troll \(warcraft\), blue skin, tusks, interspecies

tauren with hooves, horns, furry male, furry with non-furry, interspecies

worgen, furry male, furry with non-furry, interspecies

goblin, green skin, interspecies

SD 1.5 settings:

Human Warlock Assumi. It is original character of artist Shina but I suppose you know her from noname55 videos and Shina arts.

LoRA was trained on Animefull due to best compitability with all anime / 2.5D checkpoint models.

0.8 - 0.95 strength of Lora is the best radius. 

Clip skip 2.

Some necessary tokens for better experience:

Appearance:

Assumi, 1girl,
red hair, short hair, hair bun, lips, makeup, lipstick, yellow eyes, detailed face, jewelry, earrings,

optional (without outfit): choker

Sexy warlock outfit:
highleg leotard, shoulder armor, cleavage cutout, (fishnet gloves:1.1), fishnet thighhighs, high heels

optional: fishnet top

General advices for generating:

I recommend you next prompt order for NAI-based mixes (you can see it in my preview arts):

1. (highres, high quality:1.2) ("masterpiece" and "8K" kill some concepts. Be careful if you try some complex clothes or concepts.)

   Also put lighting / shadows, intricate details if you need some extra effects. Sometimes it doesn't work if style of anime or game was baked in LoRA or anime checkpoint mixes lost some concepts which exists in vanilla SD 1.5.

2. Activation word (from lora civitai page, usually character name). Describe with danbooru tags character activity, expressions, camera position;

3. Hair details, face details, jewelry, crowns, hats, etc.

4. Clothes and shoes; Or nude.

5. Body details (large breasts, cleavage). Genitals if you want to generate it.

6. Background.

Also LoRA trained with some NSFW poses. So you can try it with LoRAs or without it.

Advices for upscaling / fixing:

• use highres.fix (If you are sure that your prompt is easy for SD); I prefer x4_Fatal_anime_500000_G, animesharp, foolhardy_remacri, siax with 1.5x - 2x upscale. 0.36 denoising and 15-18 Hires fix is enough.

• Do not use "latent" upscaler because it works worse with denoisning < 0.5 but you don't want so high denoising stength because it changes your image instead of adding details.

• use extention after detailer for better faces. It is better than inpaint.

• use SD Upscale / Ultimate SD Upscale script in img2img after highres fix if you want 4K or more resolution with adding details (don't use Extras for it).

• Use inpaint and sketch for other details;

• Use Photoshop / Photopea extension for fixing hands, textures and other.

I will be glad to receive feedback from you and a demonstration of your art with my LoRA!

Other works.

https://tensor.art/u/604375505701151021