addsomefurstyle (Animagine)
sunblue
- Uploaded at
- Jul 3, 2024, 1:21 AM
- Uses
- 12.56k
- Earned
- 200,000
- Reviews
- Excellent (2)
- Trigger Words
animal ears,
- Permissions
- Allow image generation & sharing
- Allow users to download this model
- Allow commercial use of generated images
Description
This LoRA will add some fur-based elements to your image.
"This LoRA is a Generic Furry Maker."
For those who want to enjoy furry girl in a somewhat casual way.
No specific design, copyright, or character exists. It can be used for generic purposes to create your own original character.
Create your own furry girl!
Combining multiple furry type LoRAs is key.
Set all styles, character type LoRAs to a low weight (0.3 or so) and increase the values of the ones you like.
Elements, characteristics, and output trends in this LoRA.
anime-like furry girl, fox-like ears, black or brown body/clothing color, horns, muscular, big limbs, (:3 ), anime-like face (no realistic snout /muzzle, it has comical mouth ),
It does not mean that recommended inputs. That’s LoRA’s base element appears when no specified inputs.
As a special note
Use this LoRA when you want to add a furry element but don't want to make it “too furry” by adding a furry tag.
so, "furry" is not used as a trigger word about this LoRA. Since some models strongly pull their own specific image being trained by the "furry" tag, so I set a trigger word that seemed to have no effect on the test to avoid this. The intention is to add those elements to models that are weakly learned in furry.This is because it is not a good idea to use the "furry" tag as a trigger word for models that do not understand furry.
Conversely, adding “furry, anthro “ tags to a model that works well with furry tags would give good results.
Recommended base value is 0.7 Higher LoRA weight values, more furry elements appears. Lowering the LoRA weight values, more human-like.
If you set the LoRA weight values too high, It made a muscular, big-limbed beast girl. I like it personally, but it tends to be a broken picture.
How to test LoRA at this site
About the model to be used during the test, recommend those that can be used with low credits. They often have "Turbo", "Hyper" or "Lightning" in the model name and have sampling steps set to 8. You can find them in the Model Search. Please try to generate free images with these model first, as they may not be exactly what you expect. Don't waste your credits.
You will find examples at the bottom of this page under "Artworks made by this Model". Most of my examples are based on these "low cost models". Please refer to them.
other informations
This LoRA's base model is Animagin
Random appearance of horns, and not appropriate for the species. It’s intended for Personal taste. Add "horns" to the negative if unnecessary.
“big craw” I have manually re-draw the big hand & craws for all 100 images total for this LoRA. I hope it works well.
It’s a good idea about combination with detail type LoRA. And this LoRA can also be used like detail/enhancer. In that case, setting the Weight Value to 0.5~0.6 will add animal ears to the picture of the model in use, uniquely affecting the eyes, body shape and clothing.
I used large limbs in the base image, so inputting tags that make them larger will cause an overreaction. For example, tags such as “big limbs, muscular” have a strong influence.
Well, that’s all, Have a good day. Have fun!
Author's Comments.
I use it regularly myself, but don't worry about it for use this LoRA. Even if the exact same image is uploaded, it's more fun that way. Examples of my artwork are for copying settings. Feel free to use them and upload them.