Andrey Voynov

Andrey Voynov, Kfir Aberman, Daniel Cohen-Or

Text-to-Image models have introduced a remarkable leap in the evolution of machine learning, demonstrating high-quality synthesis of images from a given text-prompt. However, these powerful pretrained models still lack control handles that can guide spatial properties of the synthesized images. In this work, we introduce a universal approach to guide a pretrained text-to-image diffusion model, with a spatial map from another domain (e.g., sketch) during inference time. Unlike previous works, our method does not require to train a dedicated model or a specialized encoder for the task. Our key idea is to train a Latent Guidance Predictor (LGP) - a small, per-pixel, Multi-Layer Perceptron (MLP) that maps latent features of noisy images to spatial maps, where the deep features are extracted from the core Denoising Diffusion Probabilistic Model (DDPM) network. The LGP is trained only on a few thousand images and constitutes a differential guiding map predictor, over which the loss is computed and propagated back to push the intermediate images to agree with the spatial map. The per-pixel training offers flexibility and locality which allows the technique to perform well on out-of-domain sketches, including free-hand style drawings. We take a particular focus on the sketch-to-image translation task, revealing a robust and expressive way to generate images that follow the guidance of a sketch of arbitrary style or domain. Project page: sketch-guided-diffusion.github.io

Andrey Voynov, Qinghao Chu, Daniel Cohen-Or et al.

We introduce an Extended Textual Conditioning space in text-to-image models, referred to as $P+$. This space consists of multiple textual conditions, derived from per-layer prompts, each corresponding to a layer of the denoising U-net of the diffusion model. We show that the extended space provides greater disentangling and control over image synthesis. We further introduce Extended Textual Inversion (XTI), where the images are inverted into $P+$, and represented by per-layer tokens. We show that XTI is more expressive and precise, and converges faster than the original Textual Inversion (TI) space. The extended inversion method does not involve any noticeable trade-off between reconstruction and editability and induces more regular inversions. We conduct a series of extensive experiments to analyze and understand the properties of the new space, and to showcase the effectiveness of our method for personalizing text-to-image models. Furthermore, we utilize the unique properties of this space to achieve previously unattainable results in object-style mixing using text-to-image models. Project page: https://prompt-plus.github.io

Vladimir Kulikov, Roni Paiss, Andrey Voynov et al.

Controlled video generation has seen drastic improvements in recent years. However, editing actions and dynamic events, or inserting contents that should affect the behaviors of other objects in real-world videos, remains a major challenge. Existing trained models struggle with complex edits, likely due to the difficulty of collecting relevant training data. Similarly, existing training-free methods are inherently restricted to structure- and motion-preserving edits and do not support modification of motion or interactions. Here, we introduce DynaEdit, a training-free editing method that unlocks versatile video editing capabilities with pretrained text-to-video flow models. Our method relies on the recently introduced inversion-free approach, which does not intervene in the model internals, and is thus model-agnostic. We show that naively attempting to adapt this approach to general unconstrained editing results in severe low-frequency misalignment and high-frequency jitter. We explain the sources for these phenomena and introduce novel mechanisms for overcoming them. Through extensive experiments, we show that DynaEdit achieves state-of-the-art results on complex text-based video editing tasks, including modifying actions, inserting objects that interact with the scene, and introducing global effects.

Andrey Voynov, Amir Hertz, Moab Arar et al.

State-of-the-art diffusion models can generate highly realistic images based on various conditioning like text, segmentation, and depth. However, an essential aspect often overlooked is the specific camera geometry used during image capture. The influence of different optical systems on the final scene appearance is frequently overlooked. This study introduces a framework that intimately integrates a text-to-image diffusion model with the particular lens geometry used in image rendering. Our method is based on a per-pixel coordinate conditioning method, enabling the control over the rendering geometry. Notably, we demonstrate the manipulation of curvature properties, achieving diverse visual effects, such as fish-eye, panoramic views, and spherical texturing using a single diffusion model.

Imagen-Team-Google, Jason Baldridge, Jakob Bauer et al.

We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred over other state-of-the-art (SOTA) models at the time of evaluation. In addition, we discuss issues around safety and representation, as well as methods we used to minimize the potential harm of our models.

Amir Hertz, Andrey Voynov, Shlomi Fruchter et al.

Large-scale Text-to-Image (T2I) models have rapidly gained prominence across creative fields, generating visually compelling outputs from textual prompts. However, controlling these models to ensure consistent style remains challenging, with existing methods necessitating fine-tuning and manual intervention to disentangle content and style. In this paper, we introduce StyleAligned, a novel technique designed to establish style alignment among a series of generated images. By employing minimal `attention sharing' during the diffusion process, our method maintains style consistency across images within T2I models. This approach allows for the creation of style-consistent images using a reference style through a straightforward inversion operation. Our method's evaluation across diverse styles and text prompts demonstrates high-quality synthesis and fidelity, underscoring its efficacy in achieving consistent style across various inputs.

Daniel Garibi, Or Patashnik, Andrey Voynov et al.

Recent advancements in text-guided diffusion models have unlocked powerful image manipulation capabilities. However, applying these methods to real images necessitates the inversion of the images into the domain of the pretrained diffusion model. Achieving faithful inversion remains a challenge, particularly for more recent models trained to generate images with a small number of denoising steps. In this work, we introduce an inversion method with a high quality-to-operation ratio, enhancing reconstruction accuracy without increasing the number of operations. Building on reversing the diffusion sampling process, our method employs an iterative renoising mechanism at each inversion sampling step. This mechanism refines the approximation of a predicted point along the forward diffusion trajectory, by iteratively applying the pretrained diffusion model, and averaging these predictions. We evaluate the performance of our ReNoise technique using various sampling algorithms and models, including recent accelerated diffusion models. Through comprehensive evaluations and comparisons, we show its effectiveness in terms of both accuracy and speed. Furthermore, we confirm that our method preserves editability by demonstrating text-driven image editing on real images.

Moab Arar, Andrey Voynov, Amir Hertz et al.

Content creators often aim to create personalized images using personal subjects that go beyond the capabilities of conventional text-to-image models. Additionally, they may want the resulting image to encompass a specific location, style, ambiance, and more. Existing personalization methods may compromise personalization ability or the alignment to complex textual prompts. This trade-off can impede the fulfillment of user prompts and subject fidelity. We propose a new approach focusing on personalization methods for a \emph{single} prompt to address this issue. We term our approach prompt-aligned personalization. While this may seem restrictive, our method excels in improving text alignment, enabling the creation of images with complex and intricate prompts, which may pose a challenge for current techniques. In particular, our method keeps the personalized model aligned with a target prompt using an additional score distillation sampling term. We demonstrate the versatility of our method in multi- and single-shot settings and further show that it can compose multiple subjects or use inspiration from reference images, such as artworks. We compare our approach quantitatively and qualitatively with existing baselines and state-of-the-art techniques.

Shai Yehezkel, Omer Dahary, Andrey Voynov et al.

Denoising diffusion models excel at generating high-quality images conditioned on text prompts, yet their effectiveness heavily relies on careful guidance during the sampling process. Classifier-Free Guidance (CFG) provides a widely used mechanism for steering generation by setting the guidance scale, which balances image quality and prompt alignment. However, the choice of the guidance scale has a critical impact on the convergence toward a visually appealing and prompt-adherent image. In this work, we propose an annealing guidance scheduler which dynamically adjusts the guidance scale over time based on the conditional noisy signal. By learning a scheduling policy, our method addresses the temperamental behavior of CFG. Empirical results demonstrate that our guidance scheduler significantly enhances image quality and alignment with the text prompt, advancing the performance of text-to-image generation. Notably, our novel scheduler requires no additional activations or memory consumption, and can seamlessly replace the common classifier-free guidance, offering an improved trade-off between prompt alignment and quality.

Ryan Burgert, Charles Herrmann, Forrester Cole et al.

While generative video models have achieved remarkable fidelity and consistency, applying these capabilities to video editing remains a complex challenge. Recent research has explored motion controllability as a means to enhance text-to-video generation or image animation; however, we identify precise motion control as a promising yet under-explored paradigm for editing existing videos. In this work, we propose modifying video motion by directly editing sparse trajectories extracted from the input. We term the deviation between input and output trajectories a "motion edit" and demonstrate that this representation, when coupled with a generative backbone, enables powerful video editing capabilities. To achieve this, we introduce a pipeline for generating "motion counterfactuals", video pairs that share identical content but distinct motion, and we fine-tune a motion-conditioned video diffusion architecture on this dataset. Our approach allows for edits that start at any timestamp and propagate naturally. In a four-way head-to-head user study, our model achieves over 65 percent preference against prior work. Please see our project page: https://ryanndagreat.github.io/MotionV2V

Nir Goren, Shai Yehezkel, Omer Dahary et al.

In this paper we show that visual diffusion models can serve as effective geometric solvers: they can directly reason about geometric problems by working in pixel space. We first demonstrate this on the Inscribed Square Problem, a long-standing problem in geometry that asks whether every Jordan curve contains four points forming a square. We then extend the approach to two other well-known hard geometric problems: the Steiner Tree Problem and the Simple Polygon Problem. Our method treats each problem instance as an image and trains a standard visual diffusion model that transforms Gaussian noise into an image representing a valid approximate solution that closely matches the exact one. The model learns to transform noisy geometric structures into correct configurations, effectively recasting geometric reasoning as image generation. Unlike prior work that necessitates specialized architectures and domain-specific adaptations when applying diffusion to parametric geometric representations, we employ a standard visual diffusion model that operates on the visual representation of the problem. This simplicity highlights a surprising bridge between generative modeling and geometric problem solving. Beyond the specific problems studied here, our results point toward a broader paradigm: operating in image space provides a general and practical framework for approximating notoriously hard problems, and opens the door to tackling a far wider class of challenging geometric tasks.

Yael Vinker, Andrey Voynov, Daniel Cohen-Or et al.

A creative idea is often born from transforming, combining, and modifying ideas from existing visual examples capturing various concepts. However, one cannot simply copy the concept as a whole, and inspiration is achieved by examining certain aspects of the concept. Hence, it is often necessary to separate a concept into different aspects to provide new perspectives. In this paper, we propose a method to decompose a visual concept, represented as a set of images, into different visual aspects encoded in a hierarchical tree structure. We utilize large vision-language models and their rich latent space for concept decomposition and generation. Each node in the tree represents a sub-concept using a learned vector embedding injected into the latent space of a pretrained text-to-image model. We use a set of regularizations to guide the optimization of the embedding vectors encoded in the nodes to follow the hierarchical structure of the tree. Our method allows to explore and discover new concepts derived from the original one. The tree provides the possibility of endless visual sampling at each node, allowing the user to explore the hidden sub-concepts of the object of interest. The learned aspects in each node can be combined within and across trees to create new visual ideas, and can be used in natural language sentences to apply such aspects to new designs.

Timofey Grigoryev, Andrey Voynov, Artem Babenko

The literature has proposed several methods to finetune pretrained GANs on new datasets, which typically results in higher performance compared to training from scratch, especially in the limited-data regime. However, despite the apparent empirical benefits of GAN pretraining, its inner mechanisms were not analyzed in-depth, and understanding of its role is not entirely clear. Moreover, the essential practical details, e.g., selecting a proper pretrained GAN checkpoint, currently do not have rigorous grounding and are typically determined by trial and error. This work aims to dissect the process of GAN finetuning. First, we show that initializing the GAN training process by a pretrained checkpoint primarily affects the model's coverage rather than the fidelity of individual samples. Second, we explicitly describe how pretrained generators and discriminators contribute to the finetuning process and explain the previous evidence on the importance of pretraining both of them. Finally, as an immediate practical benefit of our analysis, we describe a simple recipe to choose an appropriate GAN checkpoint that is the most suitable for finetuning to a particular target task. Importantly, for most of the target tasks, Imagenet-pretrained GAN, despite having poor visual quality, appears to be an excellent starting point for finetuning, resembling the typical pretraining scenario of discriminative computer vision models.

Dmitry Baranchuk, Ivan Rubachev, Andrey Voynov et al.

Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of diffusion models has made them an appealing tool in several applications, including inpainting, super-resolution, and semantic editing. In this paper, we demonstrate that diffusion models can also serve as an instrument for semantic segmentation, especially in the setup when labeled data is scarce. In particular, for several pretrained diffusion models, we investigate the intermediate activations from the networks that perform the Markov step of the reverse diffusion process. We show that these activations effectively capture the semantic information from an input image and appear to be excellent pixel-level representations for the segmentation problem. Based on these observations, we describe a simple segmentation method, which can work even if only a few training images are provided. Our approach significantly outperforms the existing alternatives on several datasets for the same amount of human supervision.

Anton Cherepkov, Andrey Voynov, Artem Babenko

Generative Adversarial Networks (GANs) are currently an indispensable tool for visual editing, being a standard component of image-to-image translation and image restoration pipelines. Furthermore, GANs are especially useful for controllable generation since their latent spaces contain a wide range of interpretable directions, well suited for semantic editing operations. By gradually changing latent codes along these directions, one can produce impressive visual effects, unattainable without GANs. In this paper, we significantly expand the range of visual effects achievable with the state-of-the-art models, like StyleGAN2. In contrast to existing works, which mostly operate by latent codes, we discover interpretable directions in the space of the generator parameters. By several simple methods, we explore this space and demonstrate that it also contains a plethora of interpretable directions, which are an excellent source of non-trivial semantic manipulations. The discovered manipulations cannot be achieved by transforming the latent codes and can be used to edit both synthetic and real images. We release our code and models and hope they will serve as a handy tool for further efforts on GAN-based image editing.

Andrey Voynov, Stanislav Morozov, Artem Babenko

The recent rise of unsupervised and self-supervised learning has dramatically reduced the dependency on labeled data, providing effective image representations for transfer to downstream vision tasks. Furthermore, recent works employed these representations in a fully unsupervised setup for image classification, reducing the need for human labels on the fine-tuning stage as well. This work demonstrates that large-scale unsupervised models can also perform a more challenging object segmentation task, requiring neither pixel-level nor image-level labeling. Namely, we show that recent unsupervised GANs allow to differentiate between foreground/background pixels, providing high-quality saliency masks. By extensive comparison on standard benchmarks, we outperform existing unsupervised alternatives for object segmentation, achieving new state-of-the-art.

Andrey Voynov, Artem Babenko

The latent spaces of GAN models often have semantically meaningful directions. Moving in these directions corresponds to human-interpretable image transformations, such as zooming or recoloring, enabling a more controllable generation process. However, the discovery of such directions is currently performed in a supervised manner, requiring human labels, pretrained models, or some form of self-supervision. These requirements severely restrict a range of directions existing approaches can discover. In this paper, we introduce an unsupervised method to identify interpretable directions in the latent space of a pretrained GAN model. By a simple model-agnostic procedure, we find directions corresponding to sensible semantic manipulations without any form of (self-)supervision. Furthermore, we reveal several non-trivial findings, which would be difficult to obtain by existing methods, e.g., a direction corresponding to background removal. As an immediate practical benefit of our work, we show how to exploit this finding to achieve competitive performance for weakly-supervised saliency detection.

Andrey Voynov, Artem Babenko

In this paper, we introduce Random Path Generative Adversarial Network (RPGAN) -- an alternative design of GANs that can serve as a tool for generative model analysis. While the latent space of a typical GAN consists of input vectors, randomly sampled from the standard Gaussian distribution, the latent space of RPGAN consists of random paths in a generator network. As we show, this design allows to understand factors of variation, captured by different generator layers, providing their natural interpretability. With experiments on standard benchmarks, we demonstrate that RPGAN reveals several interesting insights about the roles that different layers play in the image generation process. Aside from interpretability, the RPGAN model also provides competitive generation quality and allows efficient incremental learning on new data.