Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

Hey there! This is the first anime LoRa I've trained, and I'm stoked to share it with you. It's one of my all-time favorite characters, and I had a blast creating and testing it with various checkpoints. It's super flexible and offers a bunch of different camera shots, including some cool close-ups.

Some checkpoints give it that authentic '90s anime vibe, both for the character and the background, like SDXL base and DreamShaper. Check out the generation data in the uploaded images for examples. Plus, you can tweak the prompt for a different look if you want to switch things up.

On the downside, long shots lack a bit of definition, just like in those older animes that didn't focus on too many details in wide shots. However, the LoRa holds the info, and with a high-res fix, you can bring out more details. The Refiner can either enhance or mess up the details, but that depends on the checkpoint, from what I've tested.

Have fun and be sure to show me your creations!

Context:

Karin Aoi, a DNA Operator from the future, travels back in time to prevent Junta Momonari from becoming the Mega-Playboy, a man who is irresistible to women and will eventually father 100 children and lead to the overpopulation of the world. However, when Karin shoots Junta with the wrong DNA-altering bullet, he starts sporadically transforming into the Mega-Playboy. Karin must now work with Junta to prevent him from becoming the Mega-Playboy permanently.

Usage:

Activation Words: k4r1n woman

After many test I recommend using these settings for a better output.

LoRa Weight: 0.6

Clip Skip: 1

Sampler: DPM++ SDE Karras

Resolution: at least 1024 x 1024 px

Don’t use ADetailer, it doesn’t blend very well, same with Restore faces. If the face is too far you can either Hires. fix or inpaint if you have enough time.

Recommended settings for Hires. fix:

Denoising strength: 0,35

Upscaler: 4xNMKD-Superscale-SP_178000_G or 4xNMKD-Superscale-_150000_G retain a lot of texture and definition on the lines. R-ESRGAN AnimeVideo gives a cool vintage look but this is just a personal preference.

Images Generated With This Model

k4r1n woman standing, close-up, happy, golden hour, backlighting, front view, background of a rooftop, anime <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
k4r1n woman standing, close-up, happy, golden hour, backlighting, front view, background of a rooftop, anime <lora:k4r1n-000005:0.6>
k4r1n woman standing, extreme close-up, front view, background of a street, anime <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
k4r1n woman standing, extreme close-up, front view, background of a street, anime <lora:k4r1n-000005:0.6>
k4r1n woman standing, extreme close-up, front view, background of a street, anime <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
k4r1n woman standing, extreme close-up, front view, background of a street, anime <lora:k4r1n-000005:0.6>
k4r1n woman standing, extreme close-up, front view, background of a street, anime <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
k4r1n woman standing, extreme close-up, front view, background of a street, anime <lora:k4r1n-000005:0.6>
realistic, k4r1n woman standing, kawaii, cute, extreme close-up eye focus, happy, front view, background of gradient fluorescent computer room, pastel tones (by wes anderson:1) <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
realistic, k4r1n woman standing, kawaii, cute, extreme close-up eye focus, happy, front view, background of gradient fluorescent computer room, pastel tones (by wes anderson:1) <lora:k4r1n-000005:0.6>
k4r1n woman standing, close-up, happy, golden hour, backlighting, front view, background of a rooftop, anime <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
k4r1n woman standing, close-up, happy, golden hour, backlighting, front view, background of a rooftop, anime <lora:k4r1n-000005:0.6>
k4r1n woman standing, medium-shot, front view, background of a street, anime <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
k4r1n woman standing, medium-shot, front view, background of a street, anime <lora:k4r1n-000005:0.6>
k4r1n woman standing, close-up, happy, golden hour, backlighting, front view, background of a rooftop, anime <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
k4r1n woman standing, close-up, happy, golden hour, backlighting, front view, background of a rooftop, anime <lora:k4r1n-000005:0.6>
realistic, k4r1n woman standing, kawaii, cute, medium shot, happy, front view, background of gradient fluorescent, pastel tones (by wes anderson:1) <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
realistic, k4r1n woman standing, kawaii, cute, medium shot, happy, front view, background of gradient fluorescent, pastel tones (by wes anderson:1) <lora:k4r1n-000005:0.6>
realistic, k4r1n woman sitting, kawaii, cute, extreme medium shot, happy, from side, background of gradient fluorescent computer room, pastel tones (by wes anderson:1) <lora:k4r1n-000005:0.6>
N/A
Hidden For Public Users
realistic, k4r1n woman sitting, kawaii, cute, extreme medium shot, happy, from side, background of gradient fluorescent computer room, pastel tones (by wes anderson:1) <lora:k4r1n-000005:0.6>

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Your All-in-One AI Image Solution

AIEasyImage brings AI image technology to everyone. Create stunning visuals, edit like a pro, and develop your unique style – all with the power of AI. No technical skills required!