The Notebook demo can't work

[MuQY1818]

I can not use the updated weight , it cannot be loaded！ what's wrong?

[MuQY1818]

Ohi deal with it, I use the v1 parameters.However, I use v2 model ,thx

[AyushRanjan15]

I experienced the same issue. The things works but the default values in the 'photomaker_demo.ipynb' does not work by itself.

In the

photomaker_ckpt = hf_hub_download(repo_id="TencentARC/PhotoMaker", filename="photomaker-v1.bin", repo_type="model")

The photomaker_ckpt is using v1 values

pipe = PhotoMakerStableDiffusionXLPipeline.from_pretrained(
    base_model_path,
    torch_dtype=torch.bfloat16,
    use_safetensors=True,
    variant="fp16",
).to(device)

pipe.load_photomaker_adapter(
    os.path.dirname(photomaker_ckpt),
    subfolder="",
    weight_name=os.path.basename(photomaker_ckpt),
    trigger_word="img"
)

Uses v2 by default. This leads the error.

Snippent from photomaker/pipeline.py

class PhotoMakerStableDiffusionXLPipeline(StableDiffusionXLPipeline):
    @validate_hf_hub_args
    def load_photomaker_adapter(
        self,
        pretrained_model_name_or_path_or_dict: Union[str, Dict[str, torch.Tensor]],
        weight_name: str,
        subfolder: str = '',
        trigger_word: str = 'img',
        **pm_version: str = 'v2',**
        **kwargs,
    ):