Hugging Face's logo

AshtakaOOf
/
Amedira

Text-to-Image
Safetensors
English
art
anime
stable-diffusion
Model card Files Community
Amedira / README.md
AshtakaOOf's picture
AshtakaOOf
Overhaul README.md
358514a
preview code
|
raw
history blame
No virus
8.05 kB
metadata
license: creativeml-openrail-m
language:
  - en
pipeline_tag: text-to-image
tags:
  - art
  - anime
  - stable-diffusion
library_name: safetensors

🎑 ~ Amedira ~ 🎏

Gawr Rain Sunflower Miko Miku

These are samples from bV3 without negative embeddings

🎈 ❱ A model merge using clip transfer and more

This model is capable of doing multiples styles, such as flat and 2.5d.

You can also prompt Hololive vtubers with their danbooru tags (you will need to prompt their outfit too for some of them).

And it is somewhat compatible with LoRA and lyCORIS.

Every models in this repository should be made using some sort of clip transfer, except if said otherwise.

💡 ❱ Useful Tokens to make the most out of Amedira

  • SLE is a token that will improve eyes quality and saturation, and it come from AuroraOne.
SLE

and

masterpiece, detailed background, mksks style

Don't change the weight of these tokens

Style tokens:

Check out the AuroraOne page (most should work)

These tokens won't work very well on bV3, cV and Dreams

📥 ❱ Downloads section

These are the models I have merged and published

bV retains most of AuroraOne features

bV2 and 2.5 are somewhat competent Models

bV3 is a big improvement in my opinion

cV is a mix of both bV3 and Counterfeit 3

mV is a very good model made with more MeinaMix 10

Don't hesitate to try the inpainting versions on InvokeAI canvas.

Amedira

Dreams

The Dreams variant are experimental/accidental merges that I keep because they have unique styles.

🧬 ❱ Usage

Negative prompt 

(worst quality, low quality:1.2), [an10:fcNeg-neg:8], (etone:0.4), negative_hand-neg, nsfw, lowres, bad hands, bad anatomy, watermark

negative_hand-neg isn't needed and is very luck based

Embeddings Downloads

VAE

🥁 ❱ Credits