Nickolai Knizev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nickolai Knizev has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Alessandro Leite
INSA Rouen Normandy, University of Rouen Normandy, LITIS UR 4108, Rouen, France
1 shared publication - Marc Schoenauer
INRIA (National Institute for Research in Digital Science and Technology)
1 shared publication - Mathurin Videau
Meta AI, France and TAU, INRIA and LISN (CNRS & Univ. Paris-Saclay), France
1 shared publication - Olivier Teytaud
Thales - CortAIx, France
1 shared publication
Latest Publications
- Open Access
- 12 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 586-596
Interactive Latent Diffusion Model
This paper introduces Interactive Latent Diffusion Model (IELDM), an encapsulation of a popular text-to-image diffusion model into an Evolutionary framework, allowing the users to steer the design of images toward their goals, alleviating the tedious trial-and-error process that such tools frequently require. The users can not only designate their favourite images, allowing the system to build a surrogate model based on their goals and move in the same directions, but also click on some specific parts of the images to either locally refine the image through dedicated mutation, or recombine images by choosing on each one some regions they like. Experiments validate the benefits of IELDM, especially in a situation where Latent Diffusion Model is challenged by complex input prompts.
- 12 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 586-596
Open AccessInteractive Latent Diffusion Model
This paper introduces Interactive Latent Diffusion Model (IELDM), an encapsulation of a popular text-to-image diffusion model into an Evolutionary framework, allowing the users to steer the design of images toward their goals, alleviating the tedious trial-and-error process that such tools frequently require. The users can not only designate their favourite images, allowing the system to build a surrogate model based on their goals and move in the same directions, but also click on some specific parts of the images to either locally refine the image through dedicated mutation, or recombine images by choosing on each one some regions they like. Experiments validate the benefits of IELDM, especially in a situation where Latent Diffusion Model is challenged by complex input prompts.