import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("BlaireSilver13/fake-artist")
prompt = "-"
image = pipe(prompt).images[0]Fake-Artist
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
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 them in the Files & versions tab.
- Downloads last month
- 26
Model tree for BlaireSilver13/fake-artist
Base model
stabilityai/stable-diffusion-xl-base-1.0