text-to-image models
Generative models designed to produce images based on textual descriptions. These models leverage the relationship between language and visual content to create coherent and relevant images that correspond to specific inputs.
- Alchemist: Turning Public Text-to-Image Data into Generative Gold
- BitMark: Watermarking Bitwise Autoregressive Image Generative Models
- BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing
- CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
- DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
- Fast Data Attribution for Text-to-Image Models
- FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges
- IntrinsiX: High-Quality PBR Generation using Image Priors
- MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
- Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
- Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models
- One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models
- OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation
- Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
- Removing Concepts from Text-to-Image Models with Only Negative Samples
- SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency
- Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
- Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models
- Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models
- Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models