| _ | t2i | _ |
|---|---|---|
| Continuous, Subject-Specific Attribute Control in | t2i | Models by Identifying Semantic Directions |
| CTRLorALTer: Conditional LorALTer for Efficient 0-shot Control and Altering of | t2i | Models |
| GenVideo: One-shot target-image and shape aware video editing using | t2i | diffusion models |
| Science- | t2i | : Addressing Scientific Illusions in Image Synthesis |
| t2i | -CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-Image Generation |