mashroo/CRM at b6dcd98accbde2f73b40e444efc0c95012969675

CRM

Ctrl+K

3 contributors

Refactor device handling in generate3d function to use CPU instead of CUDA for mesh processing, ensuring compatibility with non-GPU environments. This change improves flexibility in data handling and maintains the integrity of the mesh generation process.

b6dcd98 about 1 month ago

configs
init over 1 year ago
examples
Re-added .webp images via Git LFS after history cleanup about 2 months 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. about 2 months ago
libs
Enhance Mesh class documentation by adding missing line breaks in docstrings for improved readability. Update device handling in FlexiCubes and FlexiCubesGeometry classes to default to 'cuda', ensuring consistent device usage across the application. Refactor ImageDreamDiffusion class to assert mode validity and streamline camera matrix pre-computation. about 1 month 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. about 2 months ago
util
Enhance Mesh class documentation by adding missing line breaks in docstrings for improved readability. Update device handling in FlexiCubes and FlexiCubesGeometry classes to default to 'cuda', ensuring consistent device usage across the application. Refactor ImageDreamDiffusion class to assert mode validity and streamline camera matrix pre-computation. about 1 month ago
.gitattributes

1.77 kB

Track .webp images with Git LFS about 2 months 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 2 months ago
app.py

8.56 kB

Refactor generate3d function in inference.py to enhance 3D mesh generation. Introduced new image processing steps for color and XYZ data, improved triplane feature extraction, and updated mesh export logic to utilize temporary file handling. This streamlines the rendering process and maintains compatibility with GPU devices. about 1 month ago
inference.py

2.75 kB

Refactor device handling in generate3d function to use CPU instead of CUDA for mesh processing, ensuring compatibility with non-GPU environments. This change improves flexibility in data handling and maintains the integrity of the mesh generation process. about 1 month ago
mesh.py

34.5 kB

Enhance Mesh class documentation by adding missing line breaks in docstrings for improved readability. Update device handling in FlexiCubes and FlexiCubesGeometry classes to default to 'cuda', ensuring consistent device usage across the application. Refactor ImageDreamDiffusion class to assert mode validity and streamline camera matrix pre-computation. about 1 month ago
pipelines.py

6.63 kB

Update device handling in TwoStagePipeline to default to 'cuda' and adjust model loading to use 'cpu' for compatibility. Ensure consistent device usage across stages and improve code clarity. about 1 month ago
requirements.txt

357 Bytes

Update requirements.txt to include rembg library for background removal functionality, enhancing the application's capabilities in image processing. about 1 month ago