search

pushpendra910 / Stable-Diffusion

This repo contains code for the stable diffusion model and its conversion to tensorflow lite models.
Other
4 stars 1 forks source link

Failed to run main.py #2

Open ZTMIDGO opened 1 year ago

ZTMIDGO commented 1 year ago

Error message

Traceback (most recent call last): File "D:\python\diffusion-tflite\main.py", line 32, in model=Instanciate_Model.LoadModel(512,512,False,True) File "D:\python\diffusion-tflite\main.py", line 30, in LoadModel return StableDiffusion(img_height,img_weight,jit_compile,download_weights) File "D:\python\diffusion-tflite\stable_diffusion_tf\stable_diffusion.py", line 24, in init text_encoder, diffusion_model, decoder, encoder = get_models(img_height, img_width, download_weights=download_weights) File "D:\python\diffusion-tflite\stable_diffusion_tf\stable_diffusion.py", line 270, in get_models diffusion_model.load_weights(diffusion_model_weights_fpath) File "D:\python\diffusion-tflite\venv\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler raise e.with_traceback(filtered_tb) from None File "D:\python\diffusion-tflite\venv\lib\site-packages\keras\mixed_precision\autocast_variable.py", line 227, in _apply_assign_update assign_op = update_fn(value, use_locking, name, False) tensorflow.python.framework.errors_impl.InternalError: Failed copying input tensor from /job:localhost/replica:0/task:0/device:CPU:0 to /job:localhost/replica:0/task:0/device:GPU:0 in order to run _EagerConst: Dst tensor is not initialized.

pushpendra910 commented 1 year ago

This error is encountered because of the Tensorflow and GPU. Make sure you are installing all the requirements without any version changes or warnings.