Open Citramones opened 4 months ago
Of course,
pipe = PhotoMakerStableDiffusionXLPipeline.from_pretrained(
base_model_path, # can change to any base model based on SDXL
torch_dtype=torch.bfloat16,
use_safetensors=True,
variant="fp16"
).to(device)
### Load PhotoMaker checkpoint
pipe.load_photomaker_adapter(
os.path.dirname(photomaker_path),
subfolder="",
weight_name=os.path.basename(photomaker_path),
trigger_word="img" # define the trigger word
)
pipe.load_lora_weights(os.path.dirname(lora_path), weight_name=lora_model_name, adapter_name="xl_more_art-full")
pipe.set_adapters(["photomaker", "xl_more_art-full"], adapter_weights=[1.0, 0.5])
pipe.fuse_lora()
Just change the lora_path
and adapter_name
Just change the
lora_path
andadapter_name
thx, maybe u know how to correctly set the adapter_weights parameter sometimes the image turns out without any style at all, although the words triggers for lora are used and I also encountered the problem that the face also does not match the photo
Is it possible to download other lora models for sdxl 1.0 and somehow use them? and how to do this?