This is a textual inversion trained on pictures of wrestler Lita, aka April Jeanette Mendez.

I hope you enjoy this textual inversion.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

A commission of @Wiggyfreak1.

Fuki (aka Fuki Commune) is a Japanese singer, the vocalist of DOLL$BOXX and Unlucky Morpheus.

1000-step TI trained on a dataset of 18 images (kindly provided by @Wiggyfreak1) with my usual settings.

Curious about my work process? I have summarized it here.

Appreciate my work? My TIs are free, but you can always buy me a coffee. :)

Key word: The 100 octavia

Using ChilloutMix for all the photos.

DMP++ 2M Karras

20-30 steps

Use as you wish. Asking permission for AI generated material is stupid. Since everything is taken from someone else. Long live pirates! F them greedy..

This is a textual inversion trained on pictures of the character Alan Partridge, played by Actor Steve Coogan.

First time creating a TI based on a male object.

Done as requested by silkpurse . I hope it's somewhat what you wanted ;)

Not quite sure how it turned out, please let me.

Please make sure to emphasize that the subject is (male), otherwise it tends to render females.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

Key word: The 100 lexa
Using ChilloutMix for all the photos.
DMP++ 2M Karras
20-30 steps

Use as you wish. Asking permission for AI generated material is stupid. Since everything is taken from someone else. Long live pirates! F them greedy..

This is a textual inversion trained on pictures of wrestler Lita, aka Amy Dumas.

I hope you enjoy this textual inversion.

Still learning and improving the progress of the training, any feedback is welcome.

Feel free to leave me a tip if you like what I am doing :)

(RAW photo, best quality), (realistic, photo-realistic:1.3), best quality ,masterpiece, an extremely delicate and beautiful, extremely detailed ,CG ,unity ,2k wallpaper, Amazing, finely detail, masterpiece,light smile,best quality, extremely detailed CG unity 8k wallpaper,huge filesize , ultra-detailed, highres, extremely detailed, iu,asymmetrical bangs,short bangs,bangs,pureerosface_v1,beautiful detailed girl, extremely detailed eyes and face, beautiful detailed eyes,light on face,looking at viewer, straight-on, staring, closed mouth,black hair,long hair, collarbone, bare shoulders, longeyelashes,breasts,nipples,upper body, lace ,lace trim,1girl,nude, naked girl, (full body:1.3), (highly detail face: 1.5), (beautiful ponytail:0.5),beautiful detailed eyes, beautiful detailed nose, vaginal detailed, nipples, realistic face, realistic body, beautiful pussy, pussy detail, comfortable expressions, thigh spread,smile, look at viewer,(ass to camera:1.1),comfortable expressions, ((thigh spread)), (ass in the mirror:1.1),ass detail,<lora:koreanDollLikeness_v15:0.3> , <ulzzang-6500:0.4>

Negative prompt: bra, covered nipples, underwear,EasyNegative, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, skin blemishes, age spot, glans,extra fingers,fewer fingers,((watermark:2)),(white letters:1), (multi nipples), lowres, bad anatomy, bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worst quality, low qualitynormal quality, jpeg artifacts, signature, watermark, username,bad feet, {Multiple people},lowres,bad anatomy,bad hands, text, error, missing fingers,extra digit, fewer digits, cropped, worstquality, low quality, normal quality,jpegartifacts,signature, watermark, blurry,bad feet,cropped,poorly drawn hands,poorly drawn face,mutation,deformed,worst quality,low quality,normal quality,jpeg artifacts,signature,extra fingers,fewer digits,extra limbs,extra arms,extra legs,malformed limbs,fused fingers,too many fingers,long neck,cross-eyed,mutated hands,polar lowres,bad body,bad proportions,gross proportions,text,error,missing fingers,missing arms,extra arms,missing legs,wrong feet bottom render,extra digit,abdominal stretch, glans, pants, briefs, knickers, kecks, thong, {{fused fingers}}, {{bad body}}

Size: 512x1424, Seed: 4198779528, Model: chilloutmix_NiPrunedFp32Fix, Steps: 25, Sampler: DPM++ SDE Karras, CFG scale: 8.5, Model hash: fc2511737a

24 year old football (soccer) player from Switzerland.

Keira Strong is a custom character embedding for generating consistent character.

Keira is a tough woman with short fiery red hair, perfect for your barbarian woman or strong woman generations.

This embedding is trained with dataset images that is generated by AI. She's not based on any existing person or character.

Katherine Elizabeth Upton (St. Joseph, Míchigan), known as Kate Upton, is an american model and actress known for her appearence in Sports Illustrated Swimsuit Issue 2011.

She was a model for Beach Bunny ​ and Victoria's Secret.

If you want, you can invite me to a Ko-Fi!

Jenna Marbles is a former American YouTuber. Over the span of ten years, her YouTube channel has accumulated approximately 1.7 billion video views and over 20 million subscribers.

This is a Stable Diffusion textual inversion about a great actress. If you wanna test it, you can put this word on the prompt: avGdnr .

PS: The test images was made with 'vainilla' SD 1.5 model. I don't know if works on SD 2.1 .

My first embedding and attempt at recreating the nsfw artists "Calm" art. Trained with 40 images.

Using prompts like 1girl, 1boy, pointy ears, elf, colored skin usually gives the best results. For now its more or less "hit or miss". I intend on improving the embedding further. You will notice that you mostly get elf girls, which most of the training pictures consisted of.

There really is no exact trigger word, just using the embedding works for me at least. I have tested the embedding on anyhentai, MeinaHentai, revAnimated, Cetusmix, AOM3, and on everyone i got some pretty good results. So i can safely say that it works on most models.

Alot of the images i used for training contained watermarks, so you should add on the negative prompt: watermark, signature, patreon username, patreon logo,

Example images were created with very simple prompts. Some of them i used inpainting on to remove the logos and watermarks. Some i fixed the faces on. Did very little inpainting tho.

Settings that worked best for me:

Sampling Method: Euler A

Sampling steps: 20-25

CFG Scale: 6-8

Hires.fix: upscale by: 1.5x -- Hires steps: 10 -- Denoising strength: 0.3

Would love to get some feedback and see your creations :D

20 year old American influencer.

A request of @lemke.

Aline Abboud is a German journalist and TV host.

500-step TI trained on a dataset of 18 images (all of them kindly provided by @lemke himself) with my usual settings.

Curious about my work process? I have summarized it here.

Appreciate my work? My TIs are free, but you can always buy me a coffee. :)

Neil Breen, maker of the greatest legitimate, full-length, theatrical feature films such as Fateful Findings and I am Here.... Now

See samples for suggested prompts (especially negatives- next version of this will not be so desert prone).

Keyword is NeilBreen, and he likes to appear with CFG anywhere from 6-11 depending on the model. Trained on SD 1.5 w no VAE.

Roxy Striar is an actress and Youtube host.

Faith Schroder

Faith is and actress, model, and dancer. Her father, however, is a miserable piece of shit.

This is a textual inversion. If you'd prefer a LoRA of Faith, go HERE

Like my work? Buy me a beer!

[ SDv1.4, 4e-03, 5100, v/a .200 ]

AJ Applegate, famous for becoming a noteworthy CEO in the apple business. This is another embed from my archive, I'm not sure why I didn't bother to upload it earlier.

The embed has been trained on SD 1.5 and works well on most 1.5 based models. Some elements unrelated to her likeness seem to be a tad overbaked into the embedding, so make sure to specify some clothing and a background, possibly with increased token weight. I also find that it works well to use inpainting (only masked, square ratios such as 768x768) for generations with a good composition but where the face doesn't turn out optimal.

If you enjoy my creations or have a face you want to commission, consider supporting me on Ko-Fi :)