---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: '-'
  output:
    url: images/fake-artisti-02.jpg
- text: '-'
  output:
    url: images/fake-artisti-03.jpg
- text: '-'
  output:
    url: images/fake-artisti-04.jpg
- text: '-'
  output:
    url: images/fake-artisti-05.jpg
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: fake artist
license: artistic-2.0
---
# Fake-Artist

<Gallery />

## Model description 

A reflection and critique on the current state of AI artists. This LoRA was created using a market driven data curation approach. A selection of 16 of the highest recently sold pieces from an NFT collection by the top AI art grifter were captioned with CogVLM, captions were edited and trained for 40 epochs using the prodigy optimizer with a batch size of 4 and a grad accumulation of 2. After testing the epochs I chose #37 to share.

## Trigger words

You should use `fake artist` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/BlaireSilver13/fake-artist/tree/main) them in the Files & versions tab.