Chitwan Saharia

Jonathan Ho, William Chan, Chitwan Saharia et al. · deepmind

We present Imagen Video, a text-conditional video generation system based on a cascade of video diffusion models. Given a text prompt, Imagen Video generates high definition videos using a base video generation model and a sequence of interleaved spatial and temporal video super-resolution models. We describe how we scale up the system as a high definition text-to-video model including design decisions such as the choice of fully-convolutional temporal and spatial super-resolution models at certain resolutions, and the choice of the v-parameterization of diffusion models. In addition, we confirm and transfer findings from previous work on diffusion-based image generation to the video generation setting. Finally, we apply progressive distillation to our video models with classifier-free guidance for fast, high quality sampling. We find Imagen Video not only capable of generating videos of high fidelity, but also having a high degree of controllability and world knowledge, including the ability to generate diverse videos and text animations in various artistic styles and with 3D object understanding. See https://imagen.research.google/video/ for samples.

Chitwan Saharia, William Chan, Saurabh Saxena et al. · deepmind

We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding. Imagen builds on the power of large transformer language models in understanding text and hinges on the strength of diffusion models in high-fidelity image generation. Our key discovery is that generic large language models (e.g. T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis: increasing the size of the language model in Imagen boosts both sample fidelity and image-text alignment much more than increasing the size of the image diffusion model. Imagen achieves a new state-of-the-art FID score of 7.27 on the COCO dataset, without ever training on COCO, and human raters find Imagen samples to be on par with the COCO data itself in image-text alignment. To assess text-to-image models in greater depth, we introduce DrawBench, a comprehensive and challenging benchmark for text-to-image models. With DrawBench, we compare Imagen with recent methods including VQ-GAN+CLIP, Latent Diffusion Models, and DALL-E 2, and find that human raters prefer Imagen over other models in side-by-side comparisons, both in terms of sample quality and image-text alignment. See https://imagen.research.google/ for an overview of the results.

Wenhu Chen, Hexiang Hu, Chitwan Saharia et al. · deepmind

Research on text-to-image generation has witnessed significant progress in generating diverse and photo-realistic images, driven by diffusion and auto-regressive models trained on large-scale image-text data. Though state-of-the-art models can generate high-quality images of common entities, they often have difficulty generating images of uncommon entities, such as `Chortai (dog)' or `Picarones (food)'. To tackle this issue, we present the Retrieval-Augmented Text-to-Image Generator (Re-Imagen), a generative model that uses retrieved information to produce high-fidelity and faithful images, even for rare or unseen entities. Given a text prompt, Re-Imagen accesses an external multi-modal knowledge base to retrieve relevant (image, text) pairs and uses them as references to generate the image. With this retrieval step, Re-Imagen is augmented with the knowledge of high-level semantics and low-level visual details of the mentioned entities, and thus improves its accuracy in generating the entities' visual appearances. We train Re-Imagen on a constructed dataset containing (image, text, retrieval) triples to teach the model to ground on both text prompt and retrieval. Furthermore, we develop a new sampling strategy to interleave the classifier-free guidance for text and retrieval conditions to balance the text and retrieval alignment. Re-Imagen achieves significant gain on FID score over COCO and WikiImage. To further evaluate the capabilities of the model, we introduce EntityDrawBench, a new benchmark that evaluates image generation for diverse entities, from frequent to rare, across multiple object categories including dogs, foods, landmarks, birds, and characters. Human evaluation on EntityDrawBench shows that Re-Imagen can significantly improve the fidelity of generated images, especially on less frequent entities.

Rosanne Liu, Dan Garrette, Chitwan Saharia et al. · deepmind

Current image generation models struggle to reliably produce well-formed visual text. In this paper, we investigate a key contributing factor: popular text-to-image models lack character-level input features, making it much harder to predict a word's visual makeup as a series of glyphs. To quantify this effect, we conduct a series of experiments comparing character-aware vs. character-blind text encoders. In the text-only domain, we find that character-aware models provide large gains on a novel spelling task (WikiSpell). Applying our learnings to the visual domain, we train a suite of image generation models, and show that character-aware variants outperform their character-blind counterparts across a range of novel text rendering tasks (our DrawText benchmark). Our models set a much higher state-of-the-art on visual spelling, with 30+ point accuracy gains over competitors on rare words, despite training on far fewer examples.

Luyang Zhu, Dawei Yang, Tyler Zhu et al. · uw

Given two images depicting a person and a garment worn by another person, our goal is to generate a visualization of how the garment might look on the input person. A key challenge is to synthesize a photorealistic detail-preserving visualization of the garment, while warping the garment to accommodate a significant body pose and shape change across the subjects. Previous methods either focus on garment detail preservation without effective pose and shape variation, or allow try-on with the desired shape and pose but lack garment details. In this paper, we propose a diffusion-based architecture that unifies two UNets (referred to as Parallel-UNet), which allows us to preserve garment details and warp the garment for significant pose and body change in a single network. The key ideas behind Parallel-UNet include: 1) garment is warped implicitly via a cross attention mechanism, 2) garment warp and person blend happen as part of a unified process as opposed to a sequence of two separate tasks. Experimental results indicate that TryOnDiffusion achieves state-of-the-art performance both qualitatively and quantitatively.

Shekoofeh Azizi, Simon Kornblith, Chitwan Saharia et al.

Deep generative models are becoming increasingly powerful, now generating diverse high fidelity photo-realistic samples given text prompts. Have they reached the point where models of natural images can be used for generative data augmentation, helping to improve challenging discriminative tasks? We show that large-scale text-to image diffusion models can be fine-tuned to produce class conditional models with SOTA FID (1.76 at 256x256 resolution) and Inception Score (239 at 256x256). The model also yields a new SOTA in Classification Accuracy Scores (64.96 for 256x256 generative samples, improving to 69.24 for 1024x1024 samples). Augmenting the ImageNet training set with samples from the resulting models yields significant improvements in ImageNet classification accuracy over strong ResNet and Vision Transformer baselines.

Su Wang, Chitwan Saharia, Ceslee Montgomery et al.

Text-guided image editing can have a transformative impact in supporting creative applications. A key challenge is to generate edits that are faithful to input text prompts, while consistent with input images. We present Imagen Editor, a cascaded diffusion model built, by fine-tuning Imagen on text-guided image inpainting. Imagen Editor's edits are faithful to the text prompts, which is accomplished by using object detectors to propose inpainting masks during training. In addition, Imagen Editor captures fine details in the input image by conditioning the cascaded pipeline on the original high resolution image. To improve qualitative and quantitative evaluation, we introduce EditBench, a systematic benchmark for text-guided image inpainting. EditBench evaluates inpainting edits on natural and generated images exploring objects, attributes, and scenes. Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.

Hshmat Sahak, Daniel Watson, Chitwan Saharia et al.

Diffusion models have shown promising results on single-image super-resolution and other image- to-image translation tasks. Despite this success, they have not outperformed state-of-the-art GAN models on the more challenging blind super-resolution task, where the input images are out of distribution, with unknown degradations. This paper introduces SR3+, a diffusion-based model for blind super-resolution, establishing a new state-of-the-art. To this end, we advocate self-supervised training with a combination of composite, parameterized degradations for self-supervised training, and noise-conditioing augmentation during training and testing. With these innovations, a large-scale convolutional architecture, and large-scale datasets, SR3+ greatly outperforms SR3. It outperforms Real-ESRGAN when trained on the same data, with a DRealSR FID score of 36.82 vs. 37.22, which further improves to FID of 32.37 with larger models, and further still with larger training sets.

Jay Whang, Mauricio Delbracio, Hossein Talebi et al.

Image deblurring is an ill-posed problem with multiple plausible solutions for a given input image. However, most existing methods produce a deterministic estimate of the clean image and are trained to minimize pixel-level distortion. These metrics are known to be poorly correlated with human perception, and often lead to unrealistic reconstructions. We present an alternative framework for blind deblurring based on conditional diffusion models. Unlike existing techniques, we train a stochastic sampler that refines the output of a deterministic predictor and is capable of producing a diverse set of plausible reconstructions for a given input. This leads to a significant improvement in perceptual quality over existing state-of-the-art methods across multiple standard benchmarks. Our predict-and-refine approach also enables much more efficient sampling compared to typical diffusion models. Combined with a carefully tuned network architecture and inference procedure, our method is competitive in terms of distortion metrics such as PSNR. These results show clear benefits of our diffusion-based method for deblurring and challenge the widely used strategy of producing a single, deterministic reconstruction.

Chitwan Saharia, William Chan, Huiwen Chang et al.

This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and JPEG restoration. Our simple implementation of image-to-image diffusion models outperforms strong GAN and regression baselines on all tasks, without task-specific hyper-parameter tuning, architecture customization, or any auxiliary loss or sophisticated new techniques needed. We uncover the impact of an L2 vs. L1 loss in the denoising diffusion objective on sample diversity, and demonstrate the importance of self-attention in the neural architecture through empirical studies. Importantly, we advocate a unified evaluation protocol based on ImageNet, with human evaluation and sample quality scores (FID, Inception Score, Classification Accuracy of a pre-trained ResNet-50, and Perceptual Distance against original images). We expect this standardized evaluation protocol to play a role in advancing image-to-image translation research. Finally, we show that a generalist, multi-task diffusion model performs as well or better than task-specific specialist counterparts. Check out https://diffusion-palette.github.io for an overview of the results.

Jonathan Ho, Chitwan Saharia, William Chan et al.

We show that cascaded diffusion models are capable of generating high fidelity images on the class-conditional ImageNet generation benchmark, without any assistance from auxiliary image classifiers to boost sample quality. A cascaded diffusion model comprises a pipeline of multiple diffusion models that generate images of increasing resolution, beginning with a standard diffusion model at the lowest resolution, followed by one or more super-resolution diffusion models that successively upsample the image and add higher resolution details. We find that the sample quality of a cascading pipeline relies crucially on conditioning augmentation, our proposed method of data augmentation of the lower resolution conditioning inputs to the super-resolution models. Our experiments show that conditioning augmentation prevents compounding error during sampling in a cascaded model, helping us to train cascading pipelines achieving FID scores of 1.48 at 64x64, 3.52 at 128x128 and 4.88 at 256x256 resolutions, outperforming BigGAN-deep, and classification accuracy scores of 63.02% (top-1) and 84.06% (top-5) at 256x256, outperforming VQ-VAE-2.

Chitwan Saharia, Jonathan Ho, William Chan et al.

We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models to conditional image generation and performs super-resolution through a stochastic denoising process. Inference starts with pure Gaussian noise and iteratively refines the noisy output using a U-Net model trained on denoising at various noise levels. SR3 exhibits strong performance on super-resolution tasks at different magnification factors, on faces and natural images. We conduct human evaluation on a standard 8X face super-resolution task on CelebA-HQ, comparing with SOTA GAN methods. SR3 achieves a fool rate close to 50%, suggesting photo-realistic outputs, while GANs do not exceed a fool rate of 34%. We further show the effectiveness of SR3 in cascaded image generation, where generative models are chained with super-resolution models, yielding a competitive FID score of 11.3 on ImageNet.

Chitwan Saharia, William Chan, Saurabh Saxena et al.

This paper presents two strong methods, CTC and Imputer, for non-autoregressive machine translation that model latent alignments with dynamic programming. We revisit CTC for machine translation and demonstrate that a simple CTC model can achieve state-of-the-art for single-step non-autoregressive machine translation, contrary to what prior work indicates. In addition, we adapt the Imputer model for non-autoregressive machine translation and demonstrate that Imputer with just 4 generation steps can match the performance of an autoregressive Transformer baseline. Our latent alignment models are simpler than many existing non-autoregressive translation baselines; for example, we do not require target length prediction or re-scoring with an autoregressive model. On the competitive WMT'14 En$\rightarrow$De task, our CTC model achieves 25.7 BLEU with a single generation step, while Imputer achieves 27.5 BLEU with 2 generation steps, and 28.0 BLEU with 4 generation steps. This compares favourably to the autoregressive Transformer baseline at 27.8 BLEU.

William Chan, Chitwan Saharia, Geoffrey Hinton et al.

This paper presents the Imputer, a neural sequence model that generates output sequences iteratively via imputations. The Imputer is an iterative generative model, requiring only a constant number of generation steps independent of the number of input or output tokens. The Imputer can be trained to approximately marginalize over all possible alignments between the input and output sequences, and all possible generation orders. We present a tractable dynamic programming training algorithm, which yields a lower bound on the log marginal likelihood. When applied to end-to-end speech recognition, the Imputer outperforms prior non-autoregressive models and achieves competitive results to autoregressive models. On LibriSpeech test-other, the Imputer achieves 11.1 WER, outperforming CTC at 13.0 WER and seq2seq at 12.5 WER.

Konrad Zolna, Chitwan Saharia, Leonard Boussioux et al.

In adversarial imitation learning, a discriminator is trained to differentiate agent episodes from expert demonstrations representing the desired behavior. However, as the trained policy learns to be more successful, the negative examples (the ones produced by the agent) become increasingly similar to expert ones. Despite the fact that the task is successfully accomplished in some of the agent's trajectories, the discriminator is trained to output low values for them. We hypothesize that this inconsistent training signal for the discriminator can impede its learning, and consequently leads to worse overall performance of the agent. We show experimental evidence for this hypothesis and that the 'False Negatives' (i.e. successful agent episodes) significantly hinder adversarial imitation learning, which is the first contribution of this paper. Then, we propose a method to alleviate the impact of false negatives and test it on the BabyAI environment. This method consistently improves sample efficiency over the baselines by at least an order of magnitude.

Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou et al.

Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language which is a proper subset of English. The platform also provides a heuristic expert agent for the purpose of simulating a human teacher. We report baseline results and estimate the amount of human involvement that would be required to train a neural network-based agent on some of the BabyAI levels. We put forward strong evidence that current deep learning methods are not yet sufficiently sample efficient when it comes to learning a language with compositional properties.