High-Resolution Image Synthesis with Latent Diffusion Models
2021年12月20日 · Our latent diffusion models (LDMs) achieve a new state of the art for image inpainting and highly competitive performance on various tasks, including unconditional image generation, semantic scene synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.
Stable Diffusion 3: Research Paper - Stability AI
2024年3月5日 · Stable Diffusion 3 outperforms state-of-the-art text-to-image generation systems such as DALL·E 3, Midjourney v6, and Ideogram v1 in typography and prompt adherence, based on human preference evaluations.
[2307.01952] SDXL: Improving Latent Diffusion Models for High ...
2023年7月4日 · We demonstrate that SDXL shows drastically improved performance compared the previous versions of Stable Diffusion and achieves results competitive with those of black-box state-of-the-art image generators.
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion …
2024年3月18日 · We introduce Latent Adversarial Diffusion Distillation (LADD), a novel distillation approach overcoming the limitations of ADD. In contrast to pixel-based ADD, LADD utilizes generative features from pretrained latent diffusion models.
In this paper, we conduct an in-depth probing analysis and demonstrate that cross-attention maps in Stable Diffusion often contain object at-tribution information, which can result in editing failures.
Our latent diffusion models (LDMs) achieve new state of the art scores for im-age inpainting and class-conditional image synthesis and highly competitive performance on various tasks, includ-ing unconditional image generation, text-to-image synthe-sis, and super-resolution, while significantly reducing com-putational requirements compared to pix...
In this paper, we explore methods for compressing and accelerating Stable Diffusion, resulting in a final compressed model with 80% memory size reduction and a generation speed that is ∼ 4x faster, while maintaining text-to-image quality.
In this paper, we propose to uti-lize the self-attention layers in stable diffusion models to achieve this goal because the pre-trained stable diffusion model has learned inherent concepts of objects within its attention layers.
You Only Need One Step: Fast Super-Resolution with Stable Diffusion …
2024年1月30日 · In this paper, we introduce YONOS-SR, a novel stable diffusion-based approach for image super-resolution that yields state-of-the-art results using only a single DDIM step. We propose a novel scale distillation approach to train our SR model.
Paper page - SDXL: Improving Latent Diffusion Models for High ...
2023年7月4日 · We demonstrate that SDXL shows drastically improved performance compared the previous versions of Stable Diffusion and achieves results competitive with those of black-box state-of-the-art image generators.
- 某些结果已被删除