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("yihyeji/hanbok_q")
prompt = "a photo of 1 girl wearing hanbok_q"
image = pipe(prompt).images[0]YAML Metadata Error:"base_model" with value "/workspace/data3/model_checkpoints/DIFFUSION_DB/Diffusion_models/diffusers/v15/chilloutmix_NiPrunedFp16Fix/" is not valid. Use a model id from https://hf.co/models.
LoRA DreamBooth - yihyeji/hanbok_q
These are LoRA adaption weights for /workspace/data3/model_checkpoints/DIFFUSION_DB/Diffusion_models/diffusers/v15/chilloutmix_NiPrunedFp16Fix/. The weights were trained on a photo of 1 girl wearing hanbok_q using DreamBooth. You can find some example images in the following.
LoRA for the text encoder was enabled: False.
- Downloads last month
- -