Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance

Mar-27-2025, 13:18:06 GMT–Neural Information Processing Systems

Recent controllable generation approaches such as FreeControl [24] and Diffusion Self-Guidance [7] bring fine-grained spatial and appearance control to text-toimage (T2I) diffusion models without training auxiliary modules.

artificial intelligence, ctrl-x, machine learning, (16 more...)

Neural Information Processing Systems

Mar-27-2025, 13:18:06 GMT

Conferences PDF

Add feedback

Country:
- North America > United States > California (0.14)

Genre:
- Research Report > Experimental Study (0.93)

Industry:
- Information Technology (0.46)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks (1.00)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (1.00)