minseop-kwak

/

moai-checkpoints

like 0

This PR updates the model card to enhance discoverability and provide clearer information:

• Pipeline Tag: Changed pipeline_tag from image-to-image to image-to-3d. This change accurately reflects the model's capability to perform novel view image and geometry synthesis.
• Library Name: Added library_name: diffusers. The model's configuration files (e.g., _diffusers_version) and its description as being "finetuned from Stable Diffusion 2.1" provide clear evidence of diffusers compatibility, enabling automated code snippets for users.
• Content Introduction: Added an introductory sentence linking to the paper Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation and listing the authors (Min-Seop Kwak, Junho Kim, Sangdoo Yun, Dongyoon Han, Taekyoung Kim, Seungryong Kim, Jin-Hwa Kim) for immediate context.
• Existing Links: Maintained the existing arXiv links for the paper badge and in the "Model Details" section.
• Sample Usage: The existing "Basic Inference" section with its Python code snippet has been retained, as it accurately reflects the usage instructions from the GitHub repository.