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 (2)
I think you should seperate the base prompts of her young version and milf version
@wuhantutg895 thanks for the feedback! In hindsight, that would've probably been better yeah. The training data for her younger version is unfortunately very small, so its barely visible when using the base trigger. You might get better results if you mix and match the prompts a bit though.
I've tested this prompt:
HTSAmalie, brown hair, long hair, brown eyes, sidelocks, braid, AmalieDress, yellow dress, black corset, braid, jewelry, brooch, boots, gem, long sleeves, puffy sleeves, single hair bun, juliet sleeves, brown footwear,
And added those to negative prompts:
ponytail, high ponytail,
This seems to be doing the trick and the outfit can be replaced with custom prompts too. Biggest "fix" is the use of ponytail in the negatives, which steers the model towards her younger version.
Not a permanent solution, but probably better than waiting for me to retrain the model ^^ once I have some free time, I'll upload a new version
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.