1 dépôt
Awesome GitHub RepositoriesDynamic Depth Scaling
Optimizes model execution by adjusting the number of active layers or depths based on training or inference timesteps.
Distinct from Deep Learning Optimization: Focuses on timestep-dependent model depth rather than general computational graph or hardware optimization
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Dynamic Depth Scaling. Refine with filters or upvote what's useful.
Awesome Dynamic Depth Scaling GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- kohya-ss/sd-scripts
kohya-ss/sd-scripts
7,133Voir sur GitHubsd-scripts is a suite of utilities designed for fine-tuning generative models, preprocessing datasets, and converting model weights. It provides a collection of scripts for executing Stable Diffusion training through methods such as DreamBooth, textual inversion, and full fine-tuning, alongside a framework for creating and managing Low-Rank Adaptation weights. The project features specialized capabilities for model weight conversion between different architectures and precision formats. It includes tools for merging adaptation weights into base models, extracting weights from trained models,
Improves efficiency and quality by applying different model depths at various timesteps during the diffusion process.
Python
