Skip to content

how to perform inference as current app.py and given inference code is not compatible? #155

@Arslan-Mehmood1

Description

@Arslan-Mehmood1

def parse_args():
args = argparse.ArgumentParser()
args.add_argument("--pretrained_model_path", type=str, required=True)
args.add_argument("--base_model_path", type=str, default=None)
args.add_argument("--weight_dtype", type=str, default="float16")
args.add_argument("--share", action="store_true")
args.add_argument(
"--local_files_only", action="store_true", help="enable it to use cached files without requesting from the hub"
)
args.add_argument("--port", type=int, default=7860)
args = args.parse_args()

if os.path.exists(os.path.join(args.pretrained_model_path, "brushnet")):
    args.version = "ppt2"
else:
    args.version = "ppt1"

if args.base_model_path is None:
    args.base_model_path = "runwayml/stable-diffusion-v1-5"
return args

V2

Clone PowerPaint Model

git lfs clone https://huggingface.co/JunhaoZhuang/PowerPaint_v2/ ./checkpoints/ppt-v2

python app.py --share --version ppt-v2 --checkpoint_dir checkpoints/ppt-v2

Error in loading models.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions