Trained entirely on screencaps
Works with other lora
Recommended weight = 0.8 - 1
The Showcase images use weight 1
This model's showcase images use "anime screencap" and "anime coloring". If your generated images have strong colors, remove both tags.
I built a fast and easy to use website for you!
Use my website to generate prompts of all the outfits, including a mix and match option with every other character I've uploaded!
Any kind of feedback on my models is highly appreciated!
I love seeing the images made with my models, dont be shy, post some!
Commission a character on my website or on Fiverr!!!
Description
FAQ
Comments (3)
Пытался сделать её лору, не получилось. Датасет 140 картинок. Теги автоматические, с помощью этого сайта. Настройки лора стандартные, которые мне предложил этот свйт для SDXL illustrious. Получилась LoRA персонажа совсем не похожая на оригинал. В чем причина?
Hiya @lentor! I'm not sure if I'm understanding everything correctly, since I am using a translator. You're saying you trained a LoRA yourself but the images generated using the lora dont look like her? This could have multiple reasons, if you want to, you can upload the safetensors file somewhere and send me the link, I can take a look at the metadata of the model to see if anything stands out :)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.