import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Alvinyz/lora-panorama-v2")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]LoRA text2image fine-tuning - Alvinyz/lora-panorama-v2
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the a small dataset collect by myself. You can find some example images in the following. This model is the result I got when I learn and practice lora tuning. It is far from perfect. Upload here just in case it might have a bit value for others. May be updated or may not.
- Downloads last month
- 3
Model tree for Alvinyz/lora-panorama-v2
Base model
runwayml/stable-diffusion-v1-5