Models>

Ke-Ta Anime Style 2B

solo, <lora:ke-ta-15:1.01>, kochiya sanae, mountain, 1girl
solo, <lora:ke-ta-15:1.01>,  mountain, 1girl,  <lora:joutouguu_mayumi:1>, armored dress, haniwa \(statue\)
solo, <lora:ke-ta-15:1.01>,  1girl, hatsune miku, concert, ;d, blue hair,
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 available for use and will generate similar character to the ones seen in the images.

Model Description by Creator

For the 2B model, it's trained on more images at a higher resolution. I've had my best luck with the LoRA strength on 1.01 and cfg set to 6

Trained from art by Ke-Ta on various booru sites, due to the questionable content in some of the training data using "nsfw, nude" in the negatives may be desirable.

Trained on google collab (thanks to @HollowStrawberry)

I've had good results on abyss orange v2 with strength set to 0.9, but you'd do well to experiment

Now it's a LoRA, much better than V1 at that, might be more flexible in the models it'll run well on too.

Images Generated With This Model

Loading...

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

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.