🎑 ~ Amedira ~ 🎏
Go check out Ahnn which my other model
Other versions examples (click to open the dropdown)
These are samples from each checkpoint excluding bV2 and bV2.5
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.
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 bV Original version (still good)
Amedira bV2.5 bV2 but with better composition
- Amedira bV2 Worse than bV and mV
Amedira bV3 The best version
Amedira cV Counterfeit style but better?
Amedira mV Bit more MeinaMix sprinkled in
The Dreams variant are experimental/accidental merges that I keep because they have unique styles.
These are somewhat obsolete because of ControlNet
📜 Changelogs (click to open the dropdown)
- Improved the README.md
- Added more images
- Overhauled README.md
- Added images
- Added bV3 inpainting version
- Added cV which is a nice Counterfeit mix
- Added link to embeddings for negative prompt
- Added Amedira bV3 which fixes bg even more + misc fixes
- Added the clip models used in 1.0 and 2.5
- Added Amedira bV2.5 which fix some downgrades from bV2
- Added Amedira bV2 which is bV but better background etc
- Added Fuzzy and Scenic Dreams variant
- Added Koofy and Ligne Dreams variant
- Added inpainting version of mV
- Added Dreams variant
- New README
- Added Amedira mV
- Amedira renamed to bV
- New huggingface repo
- Added Inpainting version
- Released Lunamedira eV1 and eV2
- Added Amedira
Add the following string of text to the start of your prompts.
sle, masterpiece, detailed background, mksks style
You can add this next string to get a flat shading style.
(flat color, pastel style, black outlines:1.2), sketch
(worst quality, low quality:1.2), [an10:fcNeg-neg:8], (etone:0.4), nsfw, lowres, bad hands, bad anatomy, watermark,
negative_hand-neg isn't needed but can be added before etone
- fcNeg-neg, Direct download
- an10, Direct download
- negative_hand-neg, Direct download
- etone by closertodeath
- WD 1.4 Blessed09 (kl-f8-anime2 but blessed down)
- Jordan_3 by deleted user
- LoraEyes by Kokoboy
- Niji Style by KoRo_
- Silicon-landscape-isolation by ashen-sensored
- lighting-locon by closertodeath
- SSAMBAtea style locon by AshtakaOOf
- Mocha Style by Tonade
- PastelMix LoRA by andite
- Little Gray Style by Cinsdia
- Dense Light by L_A_X
- more Detail by Lykon
- Youko by ayyyy22002
You are free to use this model locally but 1. You aren't allowed to redistribute on another platform. (like CivitAI or Tensor.Art) 2. I am not responsible for how this model is used to generate images.
- Downloads last month