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, perceptual data such as images and videos. Rectified flow is a recent generative model formulation that connects data and noise in a straight line. Despite its better theoretical properties and conceptual simplicity, it is not yet decisively established as standard practice. In this work, we improve existing noise sampling techniques for training rectified flow models by biasing them towards perceptually relevant scales. Through a large-scale study, we demonstrate the superior performance of this approach compared to established diffusion formulations for high-resolution text-to-image synthesis. Additionally, we present a novel transformer-based architecture for text-to-image generation that uses separate weights for the two modalities and enables a bidirectional flow of information between image and text tokens, improving text comprehension, typography, and human preference ratings. We demonstrate that this architecture follows predictable scaling trends and correlates lower validation loss to improved text-to-image synthesis as measured by various metrics and human evaluations. Our largest models outperform state-of-the-art models. Stability AI is considering making experimental data, code, and model weights publicly available.

Text-guided generative diffusion models unlock powerful image creation and editing tools. Recent approaches that edit the content of footage while retaining structure require expensive re-training for every input or rely on error-prone propagation of image edits across frames.In this work, we present a structure and content-guided video diffusion model that edits videos based on descriptions of the desired output. Conflicts between user-provided content edits and structure representations occur due to insufficient disentanglement between the two aspects. As a solution, we show that training on monocular depth estimates with varying levels of detail provides control over structure and content fidelity. A novel guidance method, enabled by joint video and image training, exposes explicit control over temporal consistency. Our experiments demonstrate a wide variety of successes; fine-grained control over output characteristics, customization based on a few reference images, and a strong user preference towards results by our model.

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. Additionally, their formulation allows for a guiding mechanism to control the image generation process without retraining. However, since these models typically operate directly in pixel space, optimization of powerful DMs often consumes hundreds of GPU days and inference is expensive due to sequential evaluations. To enable DM training on limited computational resources while retaining their quality and flexibility, we apply them in the latent space of powerful pretrained autoencoders. In contrast to previous work, training diffusion models on such a representation allows for the first time to reach a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity. By introducing cross-attention layers into the model architecture, we turn diffusion models into powerful and flexible generators for general conditioning inputs such as text or bounding boxes and high-resolution synthesis becomes possible in a convolutional manner. Our latent diffusion models (LDMs) achieve new state of the art scores for image inpainting and class-conditional image synthesis and highly competitive performance on various tasks, including unconditional image generation, text-to-image synthesis, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.

Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes local interactions. This makes them expressive, but also computationally infeasible for long sequences, such as high-resolution images. 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. We show how to (i) use CNNs to learn a context-rich vocabulary of image constituents, and in turn (ii) utilize transformers to efficiently model their composition within high-resolution images. Our approach is readily applied to conditional synthesis tasks, where both non-spatial information, such as object classes, and spatial information, such as segmentations, can control the generated image. In particular, we present the first results on semantically-guided synthesis of megapixel images with transformers. Project page at https://git.io/JLlvY.

Is a geometric model required to synthesize novel views from a single image? Being bound to local convolutions, CNNs need explicit 3D biases to model geometric transformations. In contrast, we demonstrate that a transformer-based model can synthesize entirely novel views without any hand-engineered 3D biases. This is achieved by (i) a global attention mechanism for implicitly learning long-range 3D correspondences between source and target views, and (ii) a probabilistic formulation necessary to capture the ambiguity inherent in predicting novel views from a single image, thereby overcoming the limitations of previous approaches that are restricted to relatively small viewpoint changes. We evaluate various ways to integrate 3D priors into a transformer architecture. However, our experiments show that no such geometric priors are required and that the transformer is capable of implicitly learning 3D relationships between images. Furthermore, this approach outperforms the state of the art in terms of visual quality while covering the full distribution of possible realizations.

Autoregressive models and their sequential factorization of the data likelihood have recently demonstrated great potential for image representation and synthesis. Nevertheless, they incorporate image context in a linear 1D order by attending only to previously synthesized image patches above or to the left. Not only is this unidirectional, sequential bias of attention unnatural for images as it disregards large parts of a scene until synthesis is almost complete. It also processes the entire image on a single scale, thus ignoring more global contextual information up to the gist of the entire scene. As a remedy we incorporate a coarse-to-fine hierarchy of context by combining the autoregressive formulation with a multinomial diffusion process: Whereas a multistage diffusion process successively compresses and removes information to coarsen an image, we train a Markov chain to invert this process. In each stage, the resulting autoregressive ImageBART model progressively incorporates context from previous stages in a coarse-to-fine manner. Experiments demonstrate the gain over current autoregressive models, continuous diffusion probabilistic models, and latent variable models. Moreover, the approach enables to control the synthesis process and to trade compression rate against reconstruction accuracy, while still guaranteeing visually plausible results.

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations are lacking interpretability: Since distributed coding is optimal for latent layers to improve their robustness, attributing meaning to parts of a hidden feature vector or to individual neurons is hindered. We formulate interpretation as a translation of hidden representations onto semantic concepts that are comprehensible to the user. The mapping between both domains has to be bijective so that semantic modifications in the target domain correctly alter the original representation. The proposed invertible interpretation network can be transparently applied on top of existing architectures with no need to modify or retrain them. Consequently, we translate an original representation to an equivalent yet interpretable one and backwards without affecting the expressiveness and performance of the original. The invertible interpretation network disentangles the hidden representation into separate, semantically meaningful concepts. Moreover, we present an efficient approach to define semantic concepts by only sketching two images and also an unsupervised strategy. Experimental evaluation demonstrates the wide applicability to interpretation of existing classification and image generation networks as well as to semantically guided image manipulation.

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. Recent work suggests that the power of these massive models is captured by the representations they learn. Therefore, we seek a model that can relate between different existing representations and propose to solve this task with a conditionally invertible network. This network demonstrates its capability by (i) providing generic transfer between diverse domains, (ii) enabling controlled content synthesis by allowing modification in other domains, and (iii) facilitating diagnosis of existing representations by translating them into interpretable domains such as images. Our domain transfer network can translate between fixed representations without having to learn or finetune them. This allows users to utilize various existing domain-specific expert models from the literature that had been trained with extensive computational resources. Experiments on diverse conditional image synthesis tasks, competitive image modification results and experiments on image-to-image and text-to-image generation demonstrate the generic applicability of our approach. For example, we translate between BERT and BigGAN, state-of-the-art text and image models to provide text-to-image generation, which neither of both experts can perform on their own.

Deep generative models come with the promise to learn an explainable representation for visual objects that allows image sampling, synthesis, and selective modification. The main challenge is to learn to properly model the independent latent characteristics of an object, especially its appearance and pose. We present a novel approach that learns disentangled representations of these characteristics and explains them individually. Training requires only pairs of images depicting the same object appearance, but no pose annotations. We propose an additional classifier that estimates the minimal amount of regularization required to enforce disentanglement. Thus both representations together can completely explain an image while being independent of each other. Previous methods based on adversarial approaches fail to enforce this independence, while methods based on variational approaches lead to uninformative representations. In experiments on diverse object categories, the approach successfully recombines pose and appearance to reconstruct and retarget novel synthesized images. We achieve significant improvements over state-of-the-art methods which utilize the same level of supervision, and reach performances comparable to those of pose-supervised approaches. However, we can handle the vast body of articulated object classes for which no pose models/annotations are available.

Deep generative models have demonstrated great performance in image synthesis. However, results deteriorate in case of spatial deformations, since they generate images of objects directly, rather than modeling the intricate interplay of their inherent shape and appearance. We present a conditional U-Net [30] for shape-guided image generation, conditioned on the output of a variational autoencoder for appearance. The approach is trained end-to-end on images, without requiring samples of the same object with varying pose or appearance. Experiments show that the model enables conditional image generation and transfer. Therefore, either shape or appearance can be retained from a query image, while freely altering the other. Moreover, appearance can be sampled due to its stochastic latent representation, while preserving shape. In quantitative and qualitative experiments on COCO [20], DeepFashion [21, 23], shoes [43], Market-1501 [47] and handbags [49] the approach demonstrates significant improvements over the state-of-the-art.