736 citations · 1.4k across the 12 of their papers we have counts for
15 papers
FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
Black Forest Labs, Stephen Batifol, Andreas Blattmann +18
We present evaluation results for FLUX.1 Kontext, a generative flow matching model that unifies image generation and editing. The model generates novel output views by incorporatin…
Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
Axel Sauer, Frederic Boesel, Tim Dockhorn +3
Diffusion models are the main driver of progress in image and video synthesis, but suffer from slow inference speed. Distillation methods, like the recently introduced adversarial…
Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
Patrick Esser, Sumith Kulal, Andreas Blattmann +14
Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perc…
Adversarial Diffusion Distillation
Axel Sauer, Dominik Lorenz, Andreas Blattmann +1
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 ma…
Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
Andreas Blattmann, Tim Dockhorn, Sumith Kulal +9
We present Stable Video Diffusion - a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. Recently, latent diffusion mod…
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Dustin Podell, Zion English, Kyle Lacey +5
We present SDXL, a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet backbone: The inc…
Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
Andreas Blattmann, Robin Rombach, Huan Ling +4
Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent s…
Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models
Robin Rombach, Andreas Blattmann, Björn Ommer
Novel architectures have recently improved generative image synthesis leading to excellent visual quality in various tasks. Of particular note is the field of ``AI-Art'', which has…
Semi-Parametric Neural Image Synthesis
Andreas Blattmann, Robin Rombach, Kaan Oktay +2
Novel architectures have recently improved generative image synthesis leading to excellent visual quality in various tasks. Much of this success is due to the scalability of these…
High-Resolution Image Synthesis with Latent Diffusion Models
Robin Rombach, Andreas Blattmann, Dominik Lorenz +2
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…
ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
Patrick Esser, Robin Rombach, Andreas Blattmann +1
Autoregressive models and their sequential factorization of the data likelihood have recently demonstrated great potential for image representation and synthesis. Nevertheless, the…
iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis
Andreas Blattmann, Timo Milbich, Michael Dorkenwald +1
How would a static scene react to a local poke? What are the effects on other parts of an object if you could locally push it? There will be distinctive movement, despite evident v…
Understanding Object Dynamics for Interactive Image-to-Video Synthesis
Andreas Blattmann, Timo Milbich, Michael Dorkenwald +1
What would be the effect of locally poking a static scene? We present an approach that learns naturally-looking global articulations caused by a local manipulation at a pixel level…
Stochastic Image-to-Video Synthesis using cINNs
Michael Dorkenwald, Timo Milbich, Andreas Blattmann +3
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 futur…
Behavior-Driven Synthesis of Human Dynamics
Andreas Blattmann, Timo Milbich, Michael Dorkenwald +1
Generating and representing human behavior are of major importance for various computer vision applications. Commonly, human video synthesis represents behavior as sequences of pos…