If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA.😊

DISCLAIMER: This model is extremely volatile due to the small dataset!

This model was trained using the collab/guide by holostrawberry [Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai

Checkpoint used in examples:

model.ckpt · a1079602570/animefull-final-pruned at main (huggingface.co)

I am once again open for suggestions for other styles, SFW and NSFW.

You can always drop model suggestions in the comments, both for styles that are missing on civit or those that are outdated. No guarantees but if it interests me I'll give it a go.

About the artist:

Twitter: (2) Melly @ 🎨💦💖 (@muddymelly) / X (twitter.com)

Website: Projects – art by muddymelly

Melissa Hui Wang (or muddymelly) has created a few beautifully colorized and vibrant paintings. They always have a sense of flow and chaos while still paying and incredible attention to detail.

This is the kind of stuff that is made for posters and wallpapers.

Weights & Prompts

Note that the dataset was incredibly limited. This model is therefore a bit experimental and while it resembles the original art quite well at 1.0, it is very inflexible at higher weights.

The activation prompt is:

muddymelly

Use a weight of 0.5-1.0, adjust to taste and depending on your checkpoint.

As usual I have included an XYZ plot for reference. I generally try to use 1.0 but character LoRA in particular are less restricted and more likely to resemble the character at around 0.8. Note that a weight of 1.0 is also far more likely to have a large impact on the background.

Please leave a review if you enjoyed this model or have problems with it. This helps me with improving future models and finetuning them in general. Give it a try and throw some images down below! 👇