Skip to content

Stable Diffusion_ GPU Run Error (Tensorflow 2.19.0) #698

@mohammadrezagh7192-cloud

Description

Hi Guys, Anyone can help me? Thanks.
`
import time
import keras_cv
from tensorflow import keras
import matplotlib.pyplot as plt
import tensorflow as tf

physical_devices = tf.config.list_physical_devices('GPU')
tf.config.experimental.set_memory_growth(physical_devices[0], True)

model = keras_cv.models.StableDiffusion(img_width=256, img_height=256)

images = model.text_to_image("photograph of an astronaut riding a horse", batch_size=1, num_steps=25, seed=123)
`
Encountered this:

`TypeError: Exception encountered when calling ResBlock.call().

ResourceExhaustedError.init() missing 2 required positional arguments: 'op' and 'message'

Arguments received by ResBlock.call():
• args=(['<KerasTensor shape=(None, 8, 8, 2560), dtype=float32, sparse=False, ragged=False, name=keras_tensor_156>', '<KerasTensor shape=(None, 1280), dtype=float32, sparse=False, ragged=False, name=keras_tensor_41>'],)
• kwargs=<class 'inspect._empty'>`

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions