All Images Here Are Generated By AI.

All Models

>

Black Mage [Costume] (Final Fantasy)

wideshot, full body, 1girl, bmcostume, catgirl, short blonde hair, animal ears, hands on hips,
 <lora:BlackMageCostumeV1:1>
wideshot, full body, 1girl, bmcostume, catgirl, short blonde hair, animal ears, hands on hips, <lora:BlackMageCostumeV1:1>
wideshot, upper body, 1girl, bmcostume
<lora:BlackMageCostumeV1:1>
wideshot, upper body, 1girl, bmcostume <lora:BlackMageCostumeV1:1>
wideshot, upper body, 1girl, bmcostume,
 <lora:BlackMageCostumeV1:1>
wideshot, upper body, 1girl, bmcostume, <lora:BlackMageCostumeV1:1>

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

Image posts are highly appreciated! You don't even need to leave a review. I just love to see what people are creating with my stuff.

Prompt bmcostume for default outfit. This should be enough for the costume unless mixed with a character LoRA, which may attempt to override this costume with the character's own clothing. If needed, prompt wizard hat, blue coat, striped pants, etc. as needed and it should reinforce the clothing back into the image.

Prompt black face, yellow eyes to get an actual black mage.

Costume of the Black Mage race exclusively from Final Fantasy IX, (As far as I know? Never played it.) Only made this because a friend requested images of a certain character wearing this outfit, but prompting for the very specific clothing was impossible, and my attempts at using the Vivi Ornitier LoRA available here ended pretty horribly as mixing two character LoRAs just to try and use the clothing from one on the other is an exercise in futility. So out I went to create an entire LoRA just so I could make a few requested images. So here it is.

This is my first clothing LoRA, and unlike character LoRAs, I found zero documentation or discussion on how to make them. I asked around and someone suggested making it the opposite of a character LoRA. Whereas normally I would remove tags related to a character's looks to bake in that information, I instead added tags to fully describe all the faces/hair/etc. in the images to bake out that information, and only removed tags describing the clothing. After that, still being new to clothing, I trained it on a network dimension of 32, but unhappy with the results tried 16 and 64 as well. 64 gave me the best and most consistent results. Long story short, this LoRA seems to function well as far as I can tell, with the only problem I noticed in testing being the above mentioned issue with character LoRAs. When tested with character LoRAs it seemed like there was always a fight for dominance between the character's trained in clothing and this clothing. As also mentioned above, just adding a prompt describing whatever item is missing should fix it.

Tested with Hassaku-v1.3, AbyssOrangeMix3-A1B, Anything v4.5-pruned, and the old NAI leak. Plays nice with all of them so far as I can tell.

Something, something, Ko-fi if you feel like it.

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 available for use and will generate similar character 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.