text-to-image
A task in AI involving the generation of images from textual descriptions. This challenges models to understand and interpret language while producing coherent visual outputs.
- DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models
- FSI-Edit: Frequency and Stochasticity Injection for Flexible Diffusion-Based Image Editing
- HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance
- OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models
- Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization
- REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
- Rare Text Semantics Were Always There in Your Diffusion Transformer
- Role Bias in Diffusion Models: Diagnosing and Mitigating through Intermediate Decomposition
- Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
- Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models
- Universal Few-shot Spatial Control for Diffusion Models
- Value Gradient Guidance for Flow Matching Alignment
- What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models