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("kwangjin/novel_lora")
prompt = "a photo of sks person"
image = pipe(prompt).images[0]YAML Metadata Error:"base_model" with value "../../../diffusers_ckpts/anythingv3/" is not valid. Use a model id from https://hf.co/models.
LoRA DreamBooth - kwangjin/novel_lora
These are LoRA adaption weights for ../../../diffusers_ckpts/anythingv3/. The weights were trained on a photo of sks person using DreamBooth. You can find some example images in the following.
- Downloads last month
- 1