ECLIPSE priors for kandinsky v2.2 for T2I and Personalized T2I.
ECLIPSE
community
AI & ML interests
None defined yet.
Organization Card
Fuelled by the ambition to redefine the frontiers of AI, our organization is committed to advancing the efficiency and accessibility of cutting-edge image generation technologies. We're on a mission to empower the research community by democratizing high-fidelity, customizable AI solutions, pushing the boundaries of innovation, and making state-of-the-art technologies both accessible and sustainable.
Organization GitHub: https://github.com/eclipse-t2i
Key Projects:
- [CVPR 2024] ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations. [Project Page] [GitHub] [Demo] [Checkpoint]
- [CVPR 2024] WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models. [Project Page]
- λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space. [Project Page] [GitHub] [Demo] [Checkpoint]
Collections
2
Collection of research papers published by the organization members
-
ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations
Paper • 2312.04655 • Published • 20 -
λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space
Paper • 2402.05195 • Published • 18 -
WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
Paper • 2306.04744 • Published • 1 -
ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
Paper • 2306.04695 • Published • 1
datasets
None public yet