.nojekyll

@misc{brack2022Stable,
      Anote = {./images/sega_graphic.png},
      title={The Stable Artist: Steering Semantics in Diffusion Latent Space},
      author={Manuel Brack and Patrick Schramowski and Felix Friedrich and Dominik Hintersdorf and Kristian Kersting},
      Howpublished = {arXiv preprint arXiv:2212.06013},
      year = {2022},
      month={Dez},
      Note = {Large, text-conditioned generative diffusion models have recently gained a lot of attention for their impressive performance in generating high-fidelity images from text alone. However, achieving high-quality results is almost unfeasible in a one-shot fashion. On the contrary, text-guided image generation involves the user making many slight changes to inputs in order to iteratively carve out the envisioned image. However, slight changes to the input prompt often lead to entirely different images being generated, and thus the control of the artist is limited in its granularity. To provide flexibility, we present the Stable Artist, an image editing approach enabling fine-grained control of the image generation process. The main component is semantic guidance (SEGA) which steers the diffusion process along variable numbers of semantic directions. This allows for subtle edits to images, changes in composition and style, as well as optimization of the overall artistic conception. Furthermore, SEGA enables probing of latent spaces to gain insights into the representation of concepts learned by the model, even complex ones such as 'carbon emission'. We demonstrate the Stable Artist on several tasks, showcasing high-quality image editing and composition.},
      Pages = {},
      Keywords = {Representations, Text-to-Image Synthesis, Text-Guided Image Generation, Stable Diffusion, Concepts, Semantics},
      Url={https://arxiv.org/abs/2212.06013}
}