Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Duplicated from
Zhengyi/CRM
mashroo
/
CRM
like
0
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
CRM
/
imagedream
/
ldm
/
modules
Ctrl+K
Ctrl+K
3 contributors
History:
7 commits
YoussefAnso
Ensure input tensor is on the same device as model weights in FrozenOpenCLIPEmbedder. This change improves compatibility and performance by preventing device mismatch during image encoding.
1dfd90b
10 days ago
diffusionmodules
Refactor attention module to improve xformers integration. Renamed availability flag to HAS_XFORMERS and added safe_memory_efficient_attention function for better handling of attention operations across devices. Updated related assertions and calls to ensure compatibility with systems lacking GPU support.
10 days ago
distributions
init
over 1 year ago
encoders
Ensure input tensor is on the same device as model weights in FrozenOpenCLIPEmbedder. This change improves compatibility and performance by preventing device mismatch during image encoding.
10 days ago
__init__.py
Safe
0 Bytes
init
over 1 year ago
attention.py
Safe
14.8 kB
Refactor attention module to improve xformers integration. Renamed availability flag to HAS_XFORMERS and added safe_memory_efficient_attention function for better handling of attention operations across devices. Updated related assertions and calls to ensure compatibility with systems lacking GPU support.
10 days ago
ema.py
Safe
3.21 kB
init
over 1 year ago
