https://github.com/alessioborgi/z-saslm
Accepted at the CVPR 2025 Workshop on AI for Creative Visual Content Generation, Editing and Understanding and published in the Official CVPR Workshop Procedings. Z-SASLM is a zero-shot framework for multi-style image synthesis leveraging Spherical Linear Interpolation (SLI) to achieve smooth, coherent blending—without any fine-tuning.
https://github.com/alessioborgi/z-saslm
ai blending content creative cvpr2025 diffusion dino-vit generation interpolation latent linear manipulation models spherical style-aligned visual workshop z-saslm zero-shot-learning
Last synced: about 2 months ago
JSON representation
Accepted at the CVPR 2025 Workshop on AI for Creative Visual Content Generation, Editing and Understanding and published in the Official CVPR Workshop Procedings. Z-SASLM is a zero-shot framework for multi-style image synthesis leveraging Spherical Linear Interpolation (SLI) to achieve smooth, coherent blending—without any fine-tuning.
- Host: GitHub
- URL: https://github.com/alessioborgi/z-saslm
- Owner: alessioborgi
- License: cc0-1.0
- Created: 2025-03-05T16:51:34.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-04-04T19:52:57.000Z (about 2 months ago)
- Last Synced: 2025-04-04T20:29:23.282Z (about 2 months ago)
- Topics: ai, blending, content, creative, cvpr2025, diffusion, dino-vit, generation, interpolation, latent, linear, manipulation, models, spherical, style-aligned, visual, workshop, z-saslm, zero-shot-learning
- Language: Jupyter Notebook
- Homepage: https://alessioborgi.github.io/Z-SASLM.github.io/
- Size: 446 MB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE