As with the previous embeddings from the Kardashian-Jenner tribe, most models already have quite a good grasp of how Kylie looks. This embedding is intended to provide more consistent outputs with a higher fidelity.
The embed has been trained on SD 1.5 and works well on most 1.5 based models.
If you enjoy my creations and want to support me or have a face you'd like to commission, consider supporting me on Ko-Fi or Buy Me A Coffee :)
Koh_KylieJenner
Taisiya Karpenko (Carol, Kate, Milena, Milena Angel, Milena D, Milenna, Sunna, Veronika A) is 21 years old (at the moment of shooting) Ukrainian nude model
AM006_Milena_D
Davina Michelle, born on November 12, 1995, is a Dutch singer and songwriter known for her powerful vocals and captivating performances. Growing up in Rotterdam, she discovered her passion for music at an early age and pursued her dreams relentlessly. Davina gained international recognition after her stunning cover of Pink's "What About Us" went viral, amassing millions of views on YouTube. This breakthrough led to numerous opportunities, including performing at prestigious events and collaborating with renowned artists. With her unique blend of pop, soul, and R&B, Davina has carved a niche for herself in the music industry, enchanting audiences worldwide with her emotive voice and heartfelt lyrics. Her unwavering dedication, raw talent, and magnetic stage presence continue to solidify her status as a rising star in the music industry.
davinamichelle_V1
25 year old American pornstar.
S070_KylieQuinn
Kaily A (Irma, Natasha, Sati) is 21 years old (at the moment of shooting) Ukrainian nude model
AM005_Kaily_A
要想伸好舌头的同时,角色的脸部又不走样或者被舌模的白人特征干扰的话(非白人女性),需要舌模、角色模、提示词这三方面都十分出色才行。参考聂小倩说明。
If you want to out a character's tongue damn good while keeping that character's face in shape or not being interfered with by the white features of tongue emb , you need to have excellent tongue emb, character emb, and prompt words in all three aspects.
Refer to Nie Xiaoqian's explanation.
You are not downloading a high-definition movie. There is no relationship between quality and size. In the world of deep learning, the smaller the better, just like the chip manufacturing process.
你不是在下载一部高清电影。质量和大小毫无关系。在深度学习的世界里,越小越牛逼,就如同芯片制程一样。
The generalization is quite good. Next, there will be a young version of Tong LiYa to verify the stability and reliability of this training process.
WZalex.vF
Package contents:
Checkpoint SD 1.5: https://civitai.com/models/87371
Embedding NEGATIVE: https://civitai.com/models/87375
Lora DETAIL (THIS): https://civitai.com/models/87378
Lora PHOTO: https://civitai.com/models/87376
Lora Dark Theme: https://civitai.com/models/87575
More examples here:
difConsistency_negative_v2
Naomi Watts is an actress. She has been in tons of movies, such as The Ring and King Kong.
Let me know what you think and any suggestions for who you want to see next.
naomiw1
Hannah Hoekstra is a dutch actress. She is also the face model for Aloy in the game Horizon Zero Dawn.
Let me know what you think and any suggestions on who you want to see next.
hannaH2
Leah Remini is an actress. She is most famous for her role in the TV show Kings of Queens.
Let me know what you think and any suggestions for who you want to see next.
leahr2
millie
Marta Gromova (Alison Fox, Lilu, Lily, Lily Fleur, M.G., Rita) is 19 years old (at the moment of shooting) Russian nude model
AM004_Marta_Gromova
Linnda (Lika, Kseniya) is 18 years old (at the moment of shooting) Ukrainian nude model
AM008_Linnda
Robyn Rihanna Fenty NH[3] (/riˈænə/ (listen) ree-AN-ə;born February 20, 1988) is a Barbadian singer, actress, and businesswoman. Born in Saint Michael and raised in Bridgetown, Rihanna auditioned for American record producer Evan Rogers, who invited her to the United States to record demo tapes. After signing with Def Jam in 2005, she soon gained recognition with the release of her first two studio albums, Music of the Sun (2005) and A Girl Like Me (2006), both of which were influenced by Caribbean music and peaked within the top ten on the US Billboard 200 chart.
If you like my work and you feel like it, you can invite me to a Ko-fi!
r1h4nn4
Emma Heesters is a Dutch singer, songwriter, and YouTube sensation. Born on January 8, 1996, in 's-Hertogenbosch, Netherlands, Emma's musical journey began when she started uploading cover songs on YouTube in 2008. Her captivating voice, combined with her unique renditions of popular hits, quickly gained her a massive following. With an impressive vocal range and a versatile style that spans various genres, Emma has amassed millions of subscribers and views on her YouTube channel. She has since released original music, including the successful singles "Pa Olvidarte" and "Lose You to Love Me," showcasing her talent as a songwriter. Emma Heesters continues to captivate audiences worldwide with her soulful voice, remarkable stage presence, and undeniable passion for music.
EmmaHeester_V1
This is the work that I have put the most effort into, with a very rich and varied tongue stretching action. It took almost three months from preparation to training. In the future, I will consider continuing to train the iterative version to increase the weight of this EMB, in order to cooperate with some poorly trained or poorly generalized characters EMB or Lora and also be able to stick out their tongues well.
这是我花费精力最多的一个作品,具有非常丰富多变细节的伸舌头动作。从准备到训练花费了几乎3个月的时间。后续会考虑继续训练迭代版本来增加该EMB的权重,以达到和某些训练不好或泛化差的人物emb或lora配合也能伸好舌头。
About Teeth version
Advantages: Strong expression and tension, fully demonstrating what it means to stick out your tongue with all your might.
Disadvantages: There is a lot of white feature vector pollution, and when partnering with non white female characters EMB/Lora, excellent prompt skills are required to ensure that the characters faithfully retain their faces while also being able to control their tongue extension.
Even if it is paired with the white female character EMB/Lora, it is necessary to be careful with prompts, otherwise it will also affect facial restoration.
will update a version in the future, which will keep the character's EMB face faithful(especially valuable for non white women emb)
优点:表现力和张力十足,充分展示了什么叫拼尽全力的伸舌头。
缺点:有较多的白人特征向量污染,在和非白人女性角色EMB/lora搭档时,需要高超的提示技巧才能让角色忠诚的保留脸部的同时又能驾驭伸舌头。
哪怕是和白人女性角色EMB/lora配合,也需要小心提示,不然也会影响脸部还原。
后续会更新一个版本,忠诚保留角色emb脸部的版本(对非白人女性emb特别有价值)
suckhertonguealexV2.0
Would love to see the creations people make from this. please post examples of the work. Really do want to see them.
another of my inversions. think this has captured the look reasonably but as ever i would love to see what people make from these.
big thank you to Alyila for the guide.
DEN_natasha_legeyda
Immerse yourself in the realm of 'Karmic Grid', an advanced textual embedding conceived solely from the Lasogette collection. This pioneering technology combines cutting-edge machine learning with the eccentric aesthetic spirit of Lasogette, translating its distinctive pixelated artworks into a captivating linguistic form. By distilling the essence of each unique piece in the Lasogette collection, Karmic Grid weaves together narratives that resonate with the collection's innate charm and vivacious palette. Each Lasogette artwork adds its distinct voice to this grand symphony, shaping a model that produces prose as vibrant and unconventional as the art that birthed it.
Karmic Grid is more than a technological breakthrough; it's a revolution in artistic perception and engagement. It connects visual and linguistic artistic realms, using advanced algorithms to generate text that encapsulates the heart of each Lasogette piece. This innovative approach enriches the audience's interaction with the artworks, opening new doors to exploration and understanding. The result is an extraordinary blend of technology and art, pushing the boundary of artistic expression into the realm of the written word. Karmic Grid doesn't merely reflect the Lasogette universe; it expands it, championing its unceasing commitment to exploring the infinite potential of digital art.
Since this model has been trained on VPL licensed art, it is also licensed under VPL. More information here:
https://viralpubliclicense.org/
lasogette2
A textual inversion embedding I made that was based off of Terry Davis, a computer programmer who made the operating system TempleOS with the holy resolution of 640x480 VGA with 16 colors, he also had some interesting use of vocab, but sadly he was shziophenic and passed away recently. Trigger word to start this embedding is terry-davis.
terry-davis
Would love to see the creations people make from this. please post examples of the work. Really do want to see them.
another of my inversions. think this has captured the look reasonably but as ever i would love to see what people make from these.
big thank you to Alyila for the guide.
DEN_juniper_hope
This is a download site for the negative embedding boring_e621. Its original huggingface repository, which goes into more detail about how it was trained and what it does, can be found here.
Briefly, This embedding attempts to capture what it means for an image to be uninteresting. So if you're using the Automatic1111 Stable Diffusion WebUI, you can place this file in stable-diffusion-webui\embeddings and add "by boring_e621" to your NEGATIVE prompt, and your results should be more interesting.
The title image for this model illustrates the quality improvements it can make to four simple prompts in the base SD 1.5 model.
Boring_e621 has been specifically reported to work well with the suggested models below.
by boring_e621
Nicholas Poulos is an actor, OnlyFans model and streamer from Orlando.
This model was made by request of the @F000. It was trained on a dataset of 55 images, I always try to add more images if their quality is good, and be caraful, this guy likes to be topless.
It's too hot on Civitai, feel free to get me a drink or ask for a model!
NPvl0s
May need to prompt + for bangs and - prompt for old
D36r4
One of my first embeddings form a while back. Someone asked for a link, so here it is. It uses way to many tokens, but since I don't have the training images anymore, there isn't much I can do about that.
I made it using other generations I'd done. IIRC Jenna Ortega/Wednesday was the primary subject I was prompting for so the outputs tend to take a strong resemblance to her.
I might've used someone else's lora/embedding in the making of those generations but I couldn't tell you what they were at this point. (Think Ghostly Diffusion might've been one: https://civitai.com/models/5000/ghostly-diffusion)
I recommend negative "bloodshot eyes" and positive "detailed eyes" because the embedding will try its hardest to muddy them up.
ethereal_girl
Sterre Koning is a multi-talented young artist and social media sensation. Born on December 9, 2002, in the Netherlands, Sterre rose to prominence through her exceptional singing skills, captivating audiences with her powerful voice and charismatic stage presence. With a deep passion for music, she began her journey by participating in various talent shows and competitions, eventually gaining recognition and a devoted fanbase. Sterre's talents extend beyond singing, as she is also an accomplished actress, dancer, and content creator. Her vibrant personality and engaging content have allowed her to amass a significant following on social media platforms, where she shares her experiences, covers popular songs, and connects with her fans. With her boundless talent and infectious energy, Sterre Koning continues to shine as a rising star in the entertainment industry, captivating hearts and inspiring young talents around the world.
SterreKV8
This ti was requested by @fefare
Bella Lobato is an IG model with close to 7k followers.
Feel free to leave me a tip/buy me a coffee if you like what I am doing :)
Bell4L0b4t001
The character from the not so popular Full Dive RPG anime. Very open ended model. Keeps the character, but will follow the prompts much closer with little need for weight adjustments. Works great at almost any step and scale config, compatible with most LoRAs and other embeddings.
To get the in-game outfit consistently, just type "fairy" into the prompt. Might also want to try adding "wings, thigh highs, gauntlets" for a closest match.
All training images were taken from r34, squared in paint3d, rescaled to 512x512 in birme, and then upscaled x4 in SD using R-ESRGAN. Trained at a rate of .0005 for 5k steps, but best result was around 3500-4200.
kisaragiReona
xoAeriel is an American Twitch "Variety" streamer (if by variety you mean "smoking hot woman in a hot tub" that is)
If you like my work, I'd appreciate it if you could Buy me a beer!
If you are interested in my creative process, you can read more in my blog post HERE.
And if you're feeling particularly curious, I can create a custom Textual Inversion or LoRA just for you!
[ SDv1.4, 4e-03, 5300 steps, v/s .2008 ]
xoaeriel
This ti was requested by @Mic1998
Katrina Kaif is a British-Indian actress and model.She primarily works in the Hindi film industry, commonly referred to as Bollywood. Katrina Kaif made her acting debut in 2003 with the film "Boom," but she gained recognition and popularity with her performances in movies like "Maine Pyaar Kyun Kiya?" (2005), "Namastey London" (2007), and "New York" (2009). She has since appeared in numerous successful Bollywood films, including "Ek Tha Tiger" (2012), "Dhoom 3" (2013), "Tiger Zinda Hai" (2017), and "Bharat" (2019).
Feel free to leave me a tip/buy me a coffee if you like what I am doing :)
Katr1n4K41f01
Lauren is a Scottish ASMRtist currently living in Glasgow (go Rangers!)
If you like my work, I'd appreciate it if you could Buy me a beer!
If you are interested in my creative process, you can read more in my blog post HERE.
And if you're feeling particularly curious, I can create a custom Textual Inversion or LoRA just for you!
[ SDv1.4, 4e-03, 4000 steps, v/s .2004 ]
scotmurm
Iced Mocha is an American ASMRtist with suspiciously little information about her available on the internets.
If you like my work, I'd appreciate it if you could Buy me a beer!
If you are interested in my creative process, you can read more in my blog post HERE.
And if you're feeling particularly curious, I can create a custom Textual Inversion or LoRA just for you!
[ SDv1.4, 4e-03, 4700 steps, v/s .1999 ]
icedmocha
Heather is an American pageant queen, former Miss Teen SC, model, and ASMRtist.
If you like my work, I'd appreciate it if you could Buy me a beer!
If you are interested in my creative process, you can read more in my blog post HERE.
And if you're feeling particularly curious, I can create a custom Textual Inversion or LoRA just for you!
[ SDv1.4, 4e-03, 4100 steps, v/s .1998 ]
heathered
This ti was requested by @nococif37
Ellen Tamaki is an American actress. She is mostly known for her Roles in "Charmed" as Niko Hamada and Drea Mikami in "Manifest".
Feel free to leave me a tip/buy me a coffee if you like what I am doing :)
Ell3nT4m4k101