Merge Diffusers models into a new repository
Manage and orchestrate AI workflows and datasets
Display html
Rename models in dataset leaderboard
Search and find similar datasets
Search narrators and view network connections
Create and validate structured metadata for datasets
Create a report in BoAmps format
Download datasets from a URL
Display trending datasets and spaces
Organize and process datasets using AI
Clean and process datasets
Save user inputs to datasets on Hugging Face
The SDXL/SD1.5 DARE Merger (experiment) is a dataset creation tool designed to merge Diffusers models into a new repository. It is an experimental feature aimed at enabling the combination of different model versions or configurations to create a unified dataset. This tool is particularly useful for researchers and developers working with diffusion models, allowing them to experiment with model merging and explore new possibilities in dataset creation.
• Model Merger: Enables the combination of two Diffusers models into a single repository.
• Compatibility: Works with SDXL and SD1.5 models.
• Dataset Creation: Facilitates the generation of new datasets by merging existing ones.
• Repository Support: Allows users to create a new repository from merged models.
• Experimentation: Designed as an experimental tool for exploring model merging techniques.
Is the SDXL/SD1.5 DARE Merger (experiment) suitable for production use?
No, it is currently an experimental tool and should be used for research and development purposes only.
Do I need Git to use the SDXL/SD1.5 DARE Merger (experiment)?
Yes, Git is required to clone and manage the repositories during the merging process.
Can I merge models other than SDXL and SD1.5?
The tool is specifically designed for SDXL and SD1.5 models. Support for other models is not available at this time.