Skip to content

How to use pretrained Stable Diffusion? #24

@IMasI2Cat

Description

@IMasI2Cat

Hi, I downloaded the stable diffusion base model via git clone https://huggingface.co/stabilityai/stable-diffusion-2-base. Then I call the test by srun --cpus-per-task=2 --mem-per-cpu=24G --gpus=1 --time=4320 python test_addsr.py --pretrained_model_path /home/imas/code/Repos/stable-diffusion-2-base/text_encoder/config.json --prompt '' --addsr_model_path preset/models/addsr --ram_ft_path preset/models/DAPE.pth --image_path preset/datasets/test_datasets --output_dir preset/datasets/output --start_point lr --num_inference_steps 4 --PSR_weight 0.5 (where I located the downloaded stable diffusion. However, I get the error:

OSError: Unable to load weights from pytorch checkpoint file for '/home/imas/code/Repos/stable-diffusion-2-base/text_encoder/config.json' at '/home/imas/code/Repos/stable-diffusion-2-base/text_encoder/config.json'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True. srun: error: i2c01: task 0: Exited with exit code 1.

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