Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

'No module named 'kolors.pipelines.watermark' using sample code #164

Open
lizekui opened this issue Nov 19, 2024 · 0 comments
Open

'No module named 'kolors.pipelines.watermark' using sample code #164

lizekui opened this issue Nov 19, 2024 · 0 comments

Comments

@lizekui
Copy link

lizekui commented Nov 19, 2024

(hyper) [xxx@001 Kolors]$ python3 inpainting/sample_inpainting.py ./inpainting/asset/4.png ./inpainting/asset/4_mask.png 穿着钢铁侠的衣服,高科技盔甲,主要颜色为红色和金色,并且有一些银色装饰。胸前有一个亮起的圆形反应堆装置,充满了未来科技感。超清晰,高质量,超逼真,高分辨率,最好的质量,超级细节,景深

WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
    PyTorch 1.13.1+cu117 with CUDA 1107 (you have 2.5.1+cu124)
    Python  3.10.9 (you have 3.10.14)
  Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
  Memory-efficient attention, SwiGLU, sparse and more won't be available.
  Set XFORMERS_MORE_DETAILS=1 for more details
/home/zkli/miniconda3/envs/hyper/lib/python3.10/site-packages/xformers/triton/softmax.py:30: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
  @custom_fwd(cast_inputs=torch.float16 if _triton_softmax_fp16_enabled else None)
/home/zkli/miniconda3/envs/hyper/lib/python3.10/site-packages/xformers/triton/softmax.py:87: FutureWarning: `torch.cuda.amp.custom_bwd(args...)` is deprecated. Please use `torch.amp.custom_bwd(args..., device_type='cuda')` instead.
  def backward(
/home/zkli/miniconda3/envs/hyper/lib/python3.10/site-packages/xformers/ops/swiglu_op.py:78: FutureWarning: `torch.cuda.amp.custom_fwd(args...)` is deprecated. Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead.
  def forward(cls, ctx, x, w1, b1, w2, b2, w3, b3):
/home/zkli/miniconda3/envs/hyper/lib/python3.10/site-packages/xformers/ops/swiglu_op.py:99: FutureWarning: `torch.cuda.amp.custom_bwd(args...)` is deprecated. Please use `torch.amp.custom_bwd(args..., device_type='cuda')` instead.
  def backward(cls, ctx, dx5):
/home/zkli/miniconda3/envs/hyper/lib/python3.10/site-packages/transformers/loss/loss_for_object_detection.py:28: UserWarning: A NumPy version >=1.22.4 and <2.3.0 is required for this version of SciPy (detected version 1.21.6)
  from scipy.optimize import linear_sum_assignment
Traceback (most recent call last):
  File "/data/zkli/application/diffusers/test/kolors-inpainting/Kolors/inpainting/sample_inpainting.py", line 14, in <module>
    from kolors.pipelines.pipeline_stable_diffusion_xl_chatglm_256_inpainting import StableDiffusionXLInpaintPipeline
  File "/home/zkli/miniconda3/envs/hyper/lib/python3.10/site-packages/kolors-0.1-py3.10.egg/kolors/pipelines/pipeline_stable_diffusion_xl_chatglm_256_inpainting.py", line 62, in <module>
    from .watermark import StableDiffusionXLWatermarker
ModuleNotFoundError: No module named 'kolors.pipelines.watermark'

I did not found watermark folder in repo. But code show from .watermark import StableDiffusionXLWatermarker

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant