license: creativeml-openrail-m
language:
- en
pipeline_tag: text-to-image
tags:
- art
- anime
- stable-diffusion
library_name: safetensors
∞ 218 ∞
|
|
|
|
∞ Merge of my favorite models at the time
My model journey was fairly simple, I transitioned from nai-anyv3-anyv4-cetus-aom3. This merge encompasses the later stages where I found styles I liked.
And so, I merged cetus into aom3, and then into aom2. I still feel like aom2 has the best hands of the old old models, which is why everyone uses it one way or the other.
It's far from perfect, but I used this model for around 6 months without ever feeling the need to switch to another.
Contrary to some other ai frogs I know, I'm not tired of the "samey" look.
A good image for me does not depend on quirky, or replicating specific artists styles.
Although I find that fun as well as evident in one of my next uploads.
📜 Changelogs (click to open the dropdown)
11 26 2023
- Yoinked layout
- Added images
06 22 2023
- Upload 218
∞ Usage
I use clip skip 2 and DPM++2M Karras, steps 20
But ultimately whatever you want. I've used 7+ negative embeds, but it's all preference. 0 works just as well.
Yoinked links from Amedira:
Embeddings Downloads
- fcNeg-neg, Direct download
- an10, Direct download
- negative_hand-neg, Direct download
- etone by closertodeath
VAE
- WD 1.4 Blessed09 (kl-f8-anime2 but blessed down)
- WD 1.4 (kl-f8-anime2)
∞ Credits
- Checkpoints
∞ Legal deez
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.