import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("codemanCheng/lora-trained-xl_350")
prompt = "a photo of sks cat"
image = pipe(prompt).images[0]YAML Metadata Error:"base_model" with value "/home/cas/stable-diffusion-xl-base-0.9" is not valid. Use a model id from https://hf.co/models.
LoRA DreamBooth - codemanCheng/lora-trained-xl_350
These are LoRA adaption weights for /home/cas/stable-diffusion-xl-base-0.9. The weights were trained on a photo of sks cat using DreamBooth. You can find some example images in the following.
LoRA for the text encoder was enabled: False.
- Downloads last month
- 2