∞ 218 ∞

Title

Download


elf1 elf2 spacefangel 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.



∞ 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

VAE

∞ Credits

∞ 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.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support text-to-image models for safetensors library.