Models>

Change-A-Character: Evilify Your Waifu Today!

Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting

Model Description by Creator

------------------This is deprecated now with a Locon. Go here instead.-------------------------

https://civitai.com/models/36928/change-a-character-evilify-your-waifu-v2

A for fun LORA I created as I was creating a bunch of different character ones and wanted to shake things up, this one seemed worth uploading since there wasn't anything exactly like it on Civit (even if it's not perfect and was just for fun). It was trained on AnythingV3 with 92 images.

What does it do you ask? The main purpose I use it for is to take another LORA and to slowly "corrupt" the character into an eviler form of what it started with. The classic fall from grace trope. For example, in the pictures I used as an example above (minus the cover picture being the corrupted form) I go from using the lora for Spirit Blossom Ahri weighed more heavily than mine, to the corruption lora being weighed more heavily than the Ahri one. And the changes to the character can slowly be seen happening. Using simple prompts so that you can see it's relatively easy to get a good picture out of this.

How to use it: Trigger word being CorruptA (for Corrupt Anime, I know, I'm so original). For the above examples, I started with the prompt:

<lora:ahriSpiritBlossom_v10:0.9> , <lora:corruptACharacterEvilify_corruptaV10:0.6>, CorruptA

and eventually ended at the prompt

<lora:ahriSpiritBlossom_v10:0.4> , <lora:corruptACharacterEvilify_corruptaV10:1>, CorruptA

To note, heavy weights for CorruptA >= 1 and of the base Lora <= 0.5 can create pictures that don't perfectly resemble the original character and may require a couple generations (I made it in batches of 4 for the last corruption and one picture there was generally good). Could use other tags to make sure specific parts don't change as much as well.

What next for this? For sure a version that allows the addition of womb tattoos easier/harder based on trigger words.

What next that isn't this? Probably plan to release a couple more character Loras from Anime (Ameri from Iruma-Kun, Maki from Fire Force, Makoto from P5, and Sae + Shadow Sae from P5.) Maybe some other sporadic ideas like the above though. I may also try out Locon's as I've seen they do an even better job than Lora's. Or just give me some random suggestion. That works too.

Images Generated With This Model

AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
<lora:ahriSpiritBlossom_v10:0.9> , <lora:CorruptA:0.6>, CorruptA, 1girl
N/A
Hidden For Public Users
<lora:ahriSpiritBlossom_v10:0.9> , <lora:CorruptA:0.6>, CorruptA, 1girl
<lora:ahriSpiritBlossom_v10:0.9> , <lora:CorruptA:0.6>, CorruptA, 1girl
N/A
Hidden For Public Users
<lora:ahriSpiritBlossom_v10:0.9> , <lora:CorruptA:0.6>, CorruptA, 1girl
<lora:ahriSpiritBlossom_v10:0.8> , <lora:CorruptA:0.7>, CorruptA, 1girl
N/A
Hidden For Public Users
<lora:ahriSpiritBlossom_v10:0.8> , <lora:CorruptA:0.7>, CorruptA, 1girl
1girl, CCCPposter, sovietposter,none,soviet poster, soviet
N/A
Hidden For Public Users
1girl, CCCPposter, sovietposter,none,soviet poster, soviet
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
1girl,druid,elf,flower,eyelashes,horns, beautiful,looking at viewer,forest (masterpiece, high quality:1.2),none  <lora:NonHentaiElf_v10:0.9>
N/A
Hidden For Public Users
1girl,druid,elf,flower,eyelashes,horns, beautiful,looking at viewer,forest (masterpiece, high quality:1.2),none <lora:NonHentaiElf_v10:0.9>
1girl,collared shirt, skirt,(from above:0.85),dynamic pose,hands,(face),thigh,simple background,child, <lora:den2SD:0:NONE>
N/A
Hidden For Public Users
1girl,collared shirt, skirt,(from above:0.85),dynamic pose,hands,(face),thigh,simple background,child, <lora:den2SD:0:NONE>
1girl (watercolor:1.3),vivid color, <lora:den2SD:0:NONE>
N/A
Hidden For Public Users
1girl (watercolor:1.3),vivid color, <lora:den2SD:0:NONE>
1girl,collared shirt, skirt,(from above:0.85),dynamic pose,hands,(face),thigh,simple background,child, <lora:den2niji:0:NONE>
N/A
Hidden For Public Users
1girl,collared shirt, skirt,(from above:0.85),dynamic pose,hands,(face),thigh,simple background,child, <lora:den2niji:0:NONE>
1girl (watercolor:1.3),vivid color, <lora:den2niji:0:NONE>
N/A
Hidden For Public Users
1girl (watercolor:1.3),vivid color, <lora:den2niji:0:NONE>
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting

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.

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.