no code implementations • 18 Mar 2024 • Vikram Voleti, Chun-Han Yao, Mark Boss, Adam Letts, David Pankratz, Dmitry Tochilkin, Christian Laforte, Robin Rombach, Varun Jampani
In this work, we propose SV3D that adapts image-to-video diffusion model for novel multi-view synthesis and 3D generation, thereby leveraging the generalization and multi-view consistency of the video models, while further adding explicit camera control for NVS.
no code implementations • 18 Mar 2024 • Axel Sauer, Frederic Boesel, Tim Dockhorn, Andreas Blattmann, Patrick Esser, Robin Rombach
Distillation methods, like the recently introduced adversarial diffusion distillation (ADD) aim to shift the model from many-shot to single-step inference, albeit at the cost of expensive and difficult optimization due to its reliance on a fixed pretrained DINOv2 discriminator.
1 code implementation • 5 Mar 2024 • Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Müller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, Kyle Lacey, Alex Goodwin, Yannik Marek, Robin Rombach
Rectified flow is a recent generative model formulation that connects data and noise in a straight line.
1 code implementation • 3 Jan 2024 • Suraj Patil, William Berman, Robin Rombach, Patrick von Platen
We present aMUSEd, an open-source, lightweight masked image model (MIM) for text-to-image generation based on MUSE.
no code implementations • 6 Dec 2023 • Samar Khanna, Patrick Liu, Linqi Zhou, Chenlin Meng, Robin Rombach, Marshall Burke, David Lobell, Stefano Ermon
Our method outperforms previous state-of-the-art methods for satellite image generation and is the first large-scale $\textit{generative}$ foundation model for satellite imagery.
4 code implementations • 28 Nov 2023 • Axel Sauer, Dominik Lorenz, Andreas Blattmann, Robin Rombach
We introduce Adversarial Diffusion Distillation (ADD), a novel training approach that efficiently samples large-scale foundational image diffusion models in just 1-4 steps while maintaining high image quality.
2 code implementations • None 2023 • Andreas Blattmann, Tim Dockhorn, Sumith Kulal, Daniel Mendelevitch, Maciej Kilian, Dominik Lorenz, Yam Levi, Zion English, Vikram Voleti, Adam Letts, Varun Jampani, Robin Rombach
We then explore the impact of finetuning our base model on high-quality data and train a text-to-video model that is competitive with closed-source video generation.
3 code implementations • 4 Jul 2023 • Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, Robin Rombach
We present SDXL, a latent diffusion model for text-to-image synthesis.
no code implementations • CVPR 2023 • Seung Wook Kim, Bradley Brown, Kangxue Yin, Karsten Kreis, Katja Schwarz, Daiqing Li, Robin Rombach, Antonio Torralba, Sanja Fidler
We first train a scene auto-encoder to express a set of image and pose pairs as a neural field, represented as density and feature voxel grids that can be projected to produce novel views of the scene.
2 code implementations • CVPR 2023 • Andreas Blattmann, Robin Rombach, Huan Ling, Tim Dockhorn, Seung Wook Kim, Sanja Fidler, Karsten Kreis
We first pre-train an LDM on images only; then, we turn the image generator into a video generator by introducing a temporal dimension to the latent space diffusion model and fine-tuning on encoded image sequences, i. e., videos.
Ranked #5 on Text-to-Video Generation on MSR-VTT (CLIP-FID metric)
2 code implementations • CVPR 2023 • Chenlin Meng, Robin Rombach, Ruiqi Gao, Diederik P. Kingma, Stefano Ermon, Jonathan Ho, Tim Salimans
For standard diffusion models trained on the pixel-space, our approach is able to generate images visually comparable to that of the original model using as few as 4 sampling steps on ImageNet 64x64 and CIFAR-10, achieving FID/IS scores comparable to that of the original model while being up to 256 times faster to sample from.
1 code implementation • 26 Jul 2022 • Robin Rombach, Andreas Blattmann, Björn Ommer
In RDMs, a set of nearest neighbors is retrieved from an external database during training for each training instance, and the diffusion model is conditioned on these informative samples.
2 code implementations • 25 Apr 2022 • Andreas Blattmann, Robin Rombach, Kaan Oktay, Jonas Müller, Björn Ommer
Much of this success is due to the scalability of these architectures and hence caused by a dramatic increase in model complexity and in the computational resources invested in training these models.
32 code implementations • CVPR 2022 • Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, Björn Ommer
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
Ranked #2 on Layout-to-Image Generation on COCO-Stuff 256x256
no code implementations • NeurIPS 2021 • Patrick Esser, Robin Rombach, Andreas Blattmann, Björn Ommer
Thus, in contrast to pure autoregressive models, it can solve free-form image inpainting and, in the case of conditional models, local, text-guided image modification without requiring mask-specific training.
Ranked #4 on Text-to-Image Generation on Conceptual Captions
no code implementations • 13 May 2021 • Manuel Jahn, Robin Rombach, Björn Ommer
The use of coarse-grained layouts for controllable synthesis of complex scene images via deep generative models has recently gained popularity.
1 code implementation • CVPR 2021 • Michael Dorkenwald, Timo Milbich, Andreas Blattmann, Robin Rombach, Konstantinos G. Derpanis, Björn Ommer
Video understanding calls for a model to learn the characteristic interplay between static scene content and its dynamics: Given an image, the model must be able to predict a future progression of the portrayed scene and, conversely, a video should be explained in terms of its static image content and all the remaining characteristics not present in the initial frame.
1 code implementation • ICCV 2021 • Robin Rombach, Patrick Esser, Björn Ommer
Is a geometric model required to synthesize novel views from a single image?
Ranked #1 on Novel View Synthesis on RealEstate10K
12 code implementations • CVPR 2021 • Patrick Esser, Robin Rombach, Björn Ommer
We demonstrate how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images.
Ranked #3 on Text-to-Image Generation on LHQC
1 code implementation • 4 Dec 2020 • Patrick Esser, Robin Rombach, Björn Ommer
It is tempting to think that machines are less prone to unfairness and prejudice.
1 code implementation • ECCV 2020 • Robin Rombach, Patrick Esser, Björn Ommer
To open such a black box, it is, therefore, crucial to uncover the different semantic concepts a model has learned as well as those that it has learned to be invariant to.
1 code implementation • NeurIPS 2020 • Robin Rombach, Patrick Esser, Björn Ommer
Given the ever-increasing computational costs of modern machine learning models, we need to find new ways to reuse such expert models and thus tap into the resources that have been invested in their creation.
2 code implementations • CVPR 2020 • Patrick Esser, Robin Rombach, Björn Ommer
We formulate interpretation as a translation of hidden representations onto semantic concepts that are comprehensible to the user.