Hey, welcome friend!
Beyond excited to share my second lora attempt where I switch up my training process hopefully showing improvements from my Chocho model. Biggest difference was using Animagine XL V3.1 as the base model instead of AAM XL (Anime Mix). Ino. In my humble opinion. Is best girl in Naruto. So I took special care in making this lora as I use it for personal use. I've used other loras for months now for amazing results but it doesn't seem like anyone made a version of her during the blank period (Which I see as peak design for the majority of the cast). You can prompt for all outfits she wore during this period, her Naruto Shippuden outfit, plus a bonus outfit I made myself. All outfits can be worn with a pony tail or hair down long. I decided to make an SDXL version of the lora but I do plan to release a SD1.5 version as well.
10/31/24
Happy Halloween have Fun! 👻
04/20/24 Update!!: Added SD1.5 version!!!! I personally don't think its as good as the SDXL model but its more lightweight and seems to get the job done for the most part. Same triggers as the SDXL version though I haven't done really any testing... Let me know how it its!
Key Words:
ponytail: ponytail, flower hair,
No ponytail: long hair,
Blank Period: blank period, long skirt, purple apron skirt, purple high-collared blouse, mesh arm warmers, midriff, navel, toeless footwear,
Naruto Shippuden (Note: the spelling is little different): naruto shippuuden, alternate costume, purple high-collared blouse, midriff, navel, miniskirt, bandages, thigh holster, thigh strap, sandals, mesh arm warmers,
Chef outfit: chef uniform, mesh arm warmers, white apron, toeless footwear,
Wedding Dress: pink shirt, emerald necklace, purple bracelet, long skirt, purple apron skirt, shirt tucked in,
Florida Outfit ;) : florida outfit, torn shorts, denim shorts, purple high-collared blouse, mesh arm warmers, toeless footwear, midriff, navel,
Framing the shot: full body, upper body, close-up, cropped
Suggested settings:
I wanted the pictures to come off as natural as possible, so I didn't use certain tools like Controlnet, face restore or Inpainting but I used ADetailer for some examples. Outputs are typically just what you would get from putting in a prompt and using ADetailer for the eyes only in combination with a high-res fix, which I suggest a 4x upscaler.
I trained the LORA with Clip Skip 2.
I tested with a few different XL models including a lightning model which I included best results (However the testing was brief for each. I swear I / you can make better images :D). Decided to dust of Please feel free to leave any feedback!
Have Fun,
Florida-Man
Official HF repository: (Soon)
Your contribution is greatly appreciated and helps me to create more content. If you like my model, please consider donating: https://ko-fi.com/904floridaman
I'm open to commissions.
initial release
Go ahead and upload yours!
Your query returned no results – please try removing some filters or trying a different term.