Research Areas
Authored Publications
Sort By
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
Nitesh Bharadwaj Gundavarapu
Luca Versari
Kihyuk Sohn
Agrim Gupta
Xiuye Gu
Alex Hauptmann
Boqing Gong
Lu Jiang
ICLR (2024)
Preview abstract
While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this paper, we introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images using a common token vocabulary. Equipped with this new tokenizer, we show that LLMs outperform diffusion models on standard image and video generation benchmarks including ImageNet and Kinetics. In addition, we demonstrate that our tokenizer surpasses the previously top-performing video tokenizer on two more tasks: (1) video compression comparable to the next-generation video codec (VCC) according to human evaluations, and (2) learning effective representations for action recognition tasks.
View details
VideoPoet: A Large Language Model for Zero-Shot Video Generation
Dan Kondratyuk
Xiuye Gu
Jonathan Huang
Grant Schindler
Rachel Hornung
Vighnesh Birodkar
Jimmy Yan
Ming-Chang Chiu
Hassan Akbari
Josh Dillon
Agrim Gupta
Meera Hahn
Anja Hauth
David Hendon
Alonso Martinez
Kihyuk Sohn
Xuan Yang
Huisheng Wang
Lu Jiang
ICML (2024)
Preview abstract
We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/
View details
Photorealistic Video Generation with Diffusion Models
Agrim Gupta
Kihyuk Sohn
Xiuye Gu
Fei-Fei Li
Lu Jiang
ECCV (2024)
Preview abstract
We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance. Finally, we also train a cascade of three models for the task of text-to-video generation consisting of a base latent video diffusion model, and two video super-resolution diffusion models to generate videos of 512*896 resolution at 8 frames per second.
View details
Visual Prompt Tuning for Generative Transfer Learning
Kihyuk Sohn
Huiwen Chang
Luisa Polania
Han Zhang
Lu Jiang
CVPR 2023 (2023)
Preview abstract
Transferring knowledge from an image synthesis model trained on a large dataset is a promising direction for learning generative image models from various domains efficiently. While previous works have studied GAN models, we present a recipe for learning vision transformers by generative knowledge transfer. We base our framework on state-of-the-art generative vision transformers that represent an image as a sequence of visual tokens to the autoregressive or non-autoregressive transformers. To adapt to a new domain, we employ prompt tuning, which prepends learnable tokens called prompt to the image token sequence, and introduce a new prompt design for our task. We study on a variety of visual domains, including visual task adaptation benchmark, with varying amount of training images, and show effectiveness of knowledge transfer and a significantly better image generation quality over existing works.
View details
Preview abstract
This paper studies non-autoregressive transformers for the image synthesis task from the lens of discrete diffusion models. We find that generative methods based on non-autoregressive transformers suffer from decoding compounding error due to the parallel sampling of visual tokens. To alleviate it, we introduce discrete predictor-corrector diffusion models (DPC). Predictor-corrector samplers are a recently introduced class of samplers for diffusion models which improve upon ancestral samplers by correcting the sampling distribution of intermediate diffusion states using MCMC methods. In DPC, the Langevin corrector, which does not have a direct counterpart in discrete space, is replaced with a discrete MCMC transition defined by a learned corrector kernel. The corrector kernel is trained to make the correction steps achieve asymptotic convergence, in distribution, to the real marginal of the intermediate diffusion states. Our experiments show that equipped with DPC, discrete diffusion models can achieve comparable quality to continuous diffusion models, while having orders of magnitude faster sampling times. DPC improves upon existing discrete latent space models for class-conditional image generation on ImageNet, and outperforms recent diffusion models and GANs, according to visual evaluation user studies.
View details
MAGVIT: Masked Generative Video Transformer
Kihyuk Sohn
Han Zhang
Huiwen Chang
Alex Hauptmann
Lu Jiang
CVPR (2023)
Preview abstract
This paper introduces a Masked Generative Video Transformer, named MAGVIT, for multi-task video generation. We train a single MAGVIT model and apply it to multiple video generation tasks at inference time. To this end, two new designs are proposed: an improved 3D tokenizer model to quantize a video into spatial-temporal visual tokens, and a novel technique to embed conditions inside the mask to facilitate multi-task training.
We conduct extensive experiments to demonstrate the compelling quality, efficiency, and flexibility of the proposed model.
First, MAGVIT radically improves the previous best fidelity on two video generation tasks.
In terms of efficiency, MAGVIT offers leading video generation speed at inference time, which is estimated to be one or two orders-of-magnitudes faster than other models. As for flexibility, we verified that a single trained MAGVIT is able to generically perform 8+ tasks at several video benchmarks from drastically different visual domains. We will open source our framework and models.
View details
SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs
Zhiruo Wang
Yonatan Bisk
Alex Hauptmann
Lu Jiang
NeurIPS (2023)
Preview abstract
In this work, we introduce Semantic Pyramid AutoEncoder (SPAE) for enabling frozen LLMs to perform both understanding and generation tasks involving non-linguistic modalities such as images or videos. SPAE converts between raw pixels and interpretable lexical tokens (or words) extracted from the LLM's vocabulary. The resulting tokens capture both the semantic meaning and the fine-grained details needed for visual reconstruction, effectively translating the visual content into a language comprehensible to the LLM, and empowering it to perform a wide array of multimodal tasks. Our approach is validated through in-context learning experiments with frozen PaLM 2 and GPT 3.5 on a diverse set of image understanding and generation tasks. Our method marks the first successful attempt to enable a frozen LLM to generate image content while surpassing state-of-the-art performance in image understanding tasks, under the same setting, by over 25%.
View details
Preview abstract
Recent conditional image generation methods produce images of
remarkable diversity, fidelity and realism. However, the majority of
these methods allow conditioning only on labels or text prompts, which
limits their level of control over the generation result. In this
paper, we introduce MaskSketch, a masked image generation method that
allows spatial conditioning of the generation result, using a guiding
sketch as an extra conditioning signal during sampling. MaskSketch
utilizes a pre-trained masked image generator, requires no model
training or paired supervision, and works with input sketches of
different levels of abstraction. We propose a novel parallel sampling
scheme that leverages the structural information encoded in the
intermediate self-attention maps of a masked generative transformer,
such as scene layout and object shape. Our results show that
MaskSketch achieves high image realism and fidelity to the guiding
structure. Evaluated on standard benchmark datasets, MaskSketch
outperforms state-of-the-art methods for sketch-to-image translation,
as well as generic image-to-image translation approaches.
View details
Slide Gestalt: Automatic Structure Extraction in Slide Decks for Non-Visual Access
Yi-Hao Peng
CHI 2023: ACM Conference on Human Factors in Computing Systems (2023) (to appear)
Preview abstract
Presentation slides commonly use visual patterns for structural navigation, such as titles, dividers, and build slides. However, screen readers do not capture such intention, making it time-consuming and less accessible for blind and visually impaired (BVI) users to linearly consume slides with repeated content. We present Slide Gestalt, an automatic approach that identifies the hierarchical structure in a slide deck. Slide Gestalt computes the visual and textual correspondences between slides to generate hierarchical groupings. Readers can navigate the slide deck from the higher-level section overview to the lower-level description of a slide group or individual elements interactively with our UI. We derived side consumption and authoring practices from interviews with BVI readers and sighted creators and an analysis of 100 decks. We performed our pipeline with 50 real-world slide decks and a large dataset. Feedback from eight BVI participants showed that Slide Gestalt helped navigate a slide deck by anchoring content more efficiently, compared to using accessible slides.
View details
Preview abstract
Creating visual layouts is a critical step in graphic design. Automatic generation of such layouts is essential for scalable and diverse visual designs. To advance conditional layout generation, we introduce BLT, a bidirectional layout transformer. BLT differs from previous work on transformers in adopting non-autoregressive transformers. In training, BLT learns to predict the masked attributes by attending to surrounding attributes in two directions. During inference, BLT first generates a draft layout from the input and then iteratively refines it into a high-quality layout by masking out low-confident attributes. The masks generated in both training and inference are controlled by a new hierarchical sampling policy. We verify the proposed model on six benchmarks of diverse design tasks. Experimental results demonstrate two benefits compared to the state-of-the-art layout transformer models. First, our model empowers layout transformers to fulfill controllable layout generation. Second, it achieves up to 10x speedup in generating a layout at inference time than the layout transformer baseline.
View details
