Another test lora for Anima!

Since it is test version I need your feedback very much to understand is Anima really SDXL killer or not.

Dataset is the same as for NoobAI version.

Tags:

Lara croft, brown hair, brown eyes, ponytail, necklace, large breasts, huge breasts

green leotard, cleavage cutout, belt, brown footwear, ankle boots, white socks, brown shorts, leotard under shorts

holding gun, handgun, dual wieding

tanlines, bikini tan, tan - control of tanned skin

shoulder tattoo, paw tattoo, ass tattoo, heart tattoo, leg tattoo, midriff tattoo (use first 4 tags with visible back and last without leotard. Use leg tattoo always when legs are on pic.) - tattoo;

nose ring, nipple rings, nipple bar, navel piercing, clitoris ring, nostril ring - piercing;

Tip: "nose ring" is classic variant (on left part of nose). "Nostril ring" is for bull / cow style ring in nose (at center).

Native american Lara tags:

native american, large breasts, nipples, full-body tattoo, tattoo, tan, white bodypaint, red facepaint, nude

Bimbo Lara:

alternate hairstyle, twintails, hair scrunchie, freckles, pink collar, penis earrings, bracelet, nipple rings, linked piercing, leg tattoo, nipples, huge nipples, tan, tanlines, bikini tan, midriff tattoo, female pubic hair, red lips, thick lips, thigh strap, used condom on bag, slingshot swimsuit, shrug \(clothing\), pink bag, handbag, heart o-ring

Doppelganger (don't use tag "Lara Croft" for solo):

1girl, doppelganger \(tomb raider\), partially unzipped, cleavage, orange eyes, brown eyes, red hair, black hair, brown hair, mole above mouth, sidelocks, black eyeshadow, freckles, body freckles, collarbone, latex shirt, sleeveless shirt, black shirt

R34 content:

anal hook, rope, bondage, restrained, bound wrists, bound ankles, hogtie, suspension

all fours, on floor, restrained, stationary restraints, bondage, anal object insertion, sex machine, dildo, full body, bound wrists, bound ankles

gag, gagged, ring gag (for open mouth), bit gag (for stick in mouth), tape gag (for tape on mouth)

Text:

I tagged some text in dataset and you have chances to make it (sometimes you need lucky seed or inpaint but it is real even without LLM in text encoder of SDXL). For example - text on collar "slut", text on pubic "girl pwr"

SETTINGS FOR ANIMA PREV 3:

Short guide for now:

Same aesthetic settings (masterpiece, best quality, good quality, highres, absurdres, worst quality, low quality, bad quality, lowres, extra digits in negative.) as for V-pred but you don't need "very awa" in positive and "worst aesthetic" in negative because these tags were exclusively for NoobAI V-pred.

Also don't use "score_". Anima supports these tags but they make you pics AI-slop like Pony because score-based aesthetic tags can cause overcontrast.

Generations settings:

Euler A / ER SDE for txt2img, Euler for highres fix (euler a can break backgrounds in highres fix stage so I prefer euler highres fix. If you don't have option to choose in forge / forge neo go to settings and choose "[Hires. fix]: Show checkpoint, sampler, scheduler, and cfg options"

Also I prefer "FlowMatchEulerDiscrete" scheduler instead of "SGM Uniform".

CFG 3. You can try CFG 4-5 but personally I like visual of CFG 3 more especially for 3D style pics.

30-40 steps because Anima is more gluttonous than SDXL and 10-20 highres steps, 0.25 - 0.4 denoising for highres (depends on scene, sometimes txt2img pic is already masterpiece, lol).
Adetailer - use very high pixel padding - about 176-232 pixels instead of 32 pixels because Anima understands context much better. Denoising of adetailer - 0.25-0.3.

My preview can help!