Text-to-Image
Diffusers
PyTorch
Safetensors
IFPipeline
if

Something error

#27
by primerL - opened

Hi,
Thanks for offering the amazing model, while running it i got the following error:

Traceback (most recent call last):
  File "/vhome/libo/aigc/IF-XL/generated_image.py", line 40, in <module>
    image = stage_3(prompt=prompt, image=image, generator=generator, noise_level=100).images
  File "/vhome/libo/anaconda3/envs/aigc/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/vhome/libo/anaconda3/envs/aigc/lib/python3.9/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py", line 739, in __call__
    image, has_nsfw_concept, _ = self.run_safety_checker(image, device, prompt_embeds.dtype)
  File "/vhome/libo/anaconda3/envs/aigc/lib/python3.9/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py", line 170, in run_safety_checker
    safety_checker_input = self.feature_extractor(self.numpy_to_pil(image), return_tensors="pt").to(device)
  File "/vhome/libo/anaconda3/envs/aigc/lib/python3.9/site-packages/diffusers/pipelines/pipeline_utils.py", line 1607, in numpy_to_pil
    return numpy_to_pil(images)
  File "/vhome/libo/anaconda3/envs/aigc/lib/python3.9/site-packages/diffusers/utils/pil_utils.py", line 43, in numpy_to_pil
    images = (images * 255).round().astype("uint8")
AttributeError: 'Tensor' object has no attribute 'astype'

Looking forward to your early reply

Sign up or log in to comment