import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("SG161222/RealVisXL_V2.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("anjakuzev/michael_scott_v19")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]LoRA text2image fine-tuning - anjakuzev/michael_scott_v19
These are LoRA adaption weights for SG161222/RealVisXL_V2.0. The weights were fine-tuned on the anjakuzev/michael_scott dataset. You can find some example images in the following.
LoRA for the text encoder was enabled: False.
Special VAE used for training: None.
- Downloads last month
- 2
Model tree for anjakuzev/michael_scott_v19
Base model
SG161222/RealVisXL_V2.0