mashroo/CRM at 2053232bb2567a88aca71426721514ffecd00bed

CRM

Ctrl+K

3 contributors

Refactor texture baking in vertex_color_to_uv_textured_glb function to use a hybrid approach for barycentric calculations. This change enhances accuracy while maintaining performance, replacing vectorized operations with a loop-based method for improved precision in texture generation.

2053232 26 days ago

configs
init over 1 year ago
examples
Re-added .webp images via Git LFS after history cleanup about 1 month ago
imagedream
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. 26 days ago
libs
Refactor device handling across multiple modules to enforce CUDA usage explicitly. This change ensures consistent device allocation for model operations, enhancing performance on systems with GPU support while maintaining compatibility. 26 days ago
model
Refactor app.py and inference.py to streamline image generation and mesh export processes. Removed unnecessary CPU transfers and temporary file handling, directly returning generated GLB paths. Updated mesh export in CRM model to support vertex colors and improved overall efficiency in texture mapping. 27 days ago
util
Refactor device handling across multiple modules to enforce CUDA usage explicitly. This change ensures consistent device allocation for model operations, enhancing performance on systems with GPU support while maintaining compatibility. 26 days ago
.gitattributes

1.77 kB

Track .webp images with Git LFS about 1 month ago
.gitignore

2.7 kB

fix over 1 year ago
README.md

252 Bytes

Remove unnecessary launch parameters from app.py for simplicity and update README.md to reflect the new Gradio SDK version 4.21.0. about 1 month ago
app.py

10.4 kB

Refactor device handling across multiple modules to enforce CUDA usage explicitly. This change ensures consistent device allocation for model operations, enhancing performance on systems with GPU support while maintaining compatibility. 26 days ago
inference.py

6.13 kB

Refactor texture baking in vertex_color_to_uv_textured_glb function to use a hybrid approach for barycentric calculations. This change enhances accuracy while maintaining performance, replacing vectorized operations with a loop-based method for improved precision in texture generation. 26 days ago
mesh.py

34.5 kB

Refactor gen_image function in app.py to return base64 encoded GLB data instead of a file path. Update mesh export in inference.py to return .obj file extension. Modify Mesh class to streamline GLB export and enhance texture handling, ensuring proper integration of vertex attributes. about 1 month ago
pipelines.py

6.67 kB

Refactor device handling across multiple modules to enforce CUDA usage explicitly. This change ensures consistent device allocation for model operations, enhancing performance on systems with GPU support while maintaining compatibility. 26 days ago
requirements.txt

359 Bytes

Add functionality to download the DIS ONNX model if not found locally in app.py. Updated remove_background function to call new ensure_dis_onnx_model method for improved error handling. Added requests library to requirements.txt for HTTP requests. 27 days ago