Murata Himeko\(Scarlet Fusion\), honkai 3rd, anime, murata himeko, 1girl, solo, red hair, white background, simple background, breasts, bangs, bodysuit, closed mouth, yellow eyes, glowing, red bodysuit,<lora:honkai_3rd_himeko:0.7>,
Portrait of a young man with a chiseled jawline, emerald green eyes, and tousled brown hair. He wears a Greek warrior's armor and stands on a cliff overlooking the Aegean Sea. he is holding a sign saying "AIEasyPic"
Portrait of a young man with a chiseled jawline, emerald green eyes, and tousled brown hair. He wears a Greek warrior's armor and stands on a cliff overlooking the Aegean Sea. he is holding a sign saying "AIEasyPic"
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

I trained LoRAs for 3 characters from Honkai Impact 3rd, namely: Fu_Hua\(Shadow Knight\),Murata_Himeko\(Scarlet_Fusion\),Natasha_Cioara\(Midnight_Absinthe\). I might add more in the future...

I was too optimistic about my work efficiency, and it took me a lot of time to prepare and make the training set, including manually cropping the characters from the background. Murata_Himeko\(Scarlet_Fusion\)'s training images lack a complete back view (because I have this character, and when I show her in the game, her weapon blocks the back), and I couldn't solve it. As for Fu Hua\(Shadow Knight\) and Natasha_Cioara\(Midnight_Absinthe\), there was no difficulty in blocking the back, because their weapons are different.

I used the smallest possible parameter size to train these LoRAs, for easy sharing. (But when the size is small, the fitting effect is not enough. You can leave a comment, if you all can accept a LoRA occupying nearly 300MB, the new LoRA will consider training a larger size.) In fact, the size of the parameters does not make much difference to the training time, so I'm not saving resources. My RTX3060 was too inefficient, and the time it took to sort out the training set made me miss the expected completion date, so I had to spend the equivalent of $8 of compute units using google colab pro to finish the training.

I hope these LoRAs satisfy you. According to my tests, the facial fitting effect of the characters is not very good, but I'm very busy lately, so I can only upload this flawed version for now.

I didn't clean up the captions carefully, so the trigger words may not be very accurate. You can try more tags, possible references:

Fu Hua\(Shadow Knight\), honkai 3rd, anime, 1girl, solo, white background, mask, full body, simple background, shadow, armor, boots, purple gloves, bodysuit, black footwear, grey hair, bangs, short hair, gauntlets, closed mouth, thighhighs, black bodysuit

Murata Himeko\(Scarlet Fusion\), honkai 3rd, anime, murata himeko, 1girl, solo, red hair, white background, simple background, breasts, bangs, bodysuit, closed mouth, yellow eyes, glowing, red bodysuit

Natasha Cioara\(Midnight Absinthe\), honkai 3rd, anime, 1girl, bodysuit, claws, mole under mouth, solo, black bodysuit, mole, white background, full body, hood, looking at viewer, simple background, hair over one eye, medium hair, claw \(weapon\), bangs, closed mouth, cape, black cape, standing, smile, short hair, black hair, breasts, arms up, high heels, red eyes, claw gloves

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.