All Images Here Are Generated By AI.

All Models

>

Johnny Lawrence - [Cobra Kai / Karate Kid]

Johnnylawrence person <lora:JohnnyLawrence-Lora:.8> pushing a dead body that's in closed black body-bag on a gurney.
Johnnylawrence person <lora:JohnnyLawrence-Lora:.8> pushing a dead body that's in closed black body-bag on a gurney.
Johnnylawrence person <lora:JohnnyLawrence-Lora:.8> "Waking me like one the time before And take me high all up above" . This has its inspiration on music, art, and design, cinematic
Johnnylawrence person <lora:JohnnyLawrence-Lora:.8> "Waking me like one the time before And take me high all up above" . This has its inspiration on music, art, and design, cinematic
Johnnylawrence person <lora:JohnnyLawrence-Lora:.8> in a movie still from Prometheus 2012. cyborg aliens have been created, and after being born as humans, their minds are replaced with machine bodies. johnnylawrence person is the only man with the karate skills to beat down the cyborg aliens, fight scene, karate, action sequence, directed by Gareth Edwards
Johnnylawrence person <lora:JohnnyLawrence-Lora:.8> in a movie still from Prometheus 2012. cyborg aliens have been created, and after being born as humans, their minds are replaced with machine bodies. johnnylawrence person is the only man with the karate skills to beat down the cyborg aliens, fight scene, karate, action sequence, directed by Gareth Edwards

Generate AI Images. Simple and Easy

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

Model Description by Creator

Johnny Lawrence (played by actor: William Zabka in both "Cobra Kai" and the 1980's original movie "Karate Kid"). This is a high quality LoRA extracted from a Dreambooth trained checkpoint made w/ J.Penna's Dreambooth repo (trained locally).

The trigger works are "Johnnylawrence Person". Make sure you put "JohnnyLawrence Person" in your prompt alone w/ the usual LoRA filenaming.

For best results use Hires Fix. For ultimate results use in tandem w/ 30-60% the steps modified by Controlnet w/ Canny, Openpose, shuffle, reference, or Normal_bae (for example). This model was trained w/ a lot of steps so using a lower weight than "1" in the LoRA prompt (for example .8) will allow for more malleable image generations. Prompt weighting (()) can also help.

The samples were generated with V1.5 and also RealisitcVision 2.0. It should work with most models based off of V1.x of Stable Diffusion.

*SOME OF THE IMAGE SAMPLES WERE GENERATED W/ CONTROLNET - The site doesn't mention control net w/ the metadata on images. Someone dogged me w/ a 1 vote and F'U comment for being unable to replicate my results on previous model I uploaded. If you use the data a sample and don't get the same image generation it's likely because controlnet was used. You could always download the sample image and use -that- as a reference w/ a Controlnet model. Just play around).

Try Full Demo
Quick Generate
Image quality might not be as good as what you can achieve with our full generation tool.
Placeholder
Choose A Style, Type What You Want In The Image And Click Generate
Placeholder
Choose A Style, Type What You Want In The Image 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.
Train Your Own Model

Images Generated With This Model

Loading...

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.