paper-with-me

Papers

CogView: Mastering Text-to-Image Generation via Transformers

2021-05-26 · NeurIPS 2021 12 · Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, Jie Tang

Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e.g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e.g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a recent similar work DALL-E.

📄 PDF Abstract BibTeX arXiv:2105.13290

Code (4)

THUDM/CogView 공식 구현 pytorch
JunnYu/x-transformers-paddle jax
thudm/cogview2 pytorch
thudm/visualglm-6b pytorch

Tasks

Image GenerationSuper-ResolutionText to Image GenerationText-to-Image GenerationZero-Shot Text-to-Image Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers

2022-04-28 · Ming Ding, Wendi Zheng, Wenyi Hong, Jie Tang

The development of the transformer-based text-to-image models are impeded by its slow generation and complexity for high-resolution images. In this work, we put forward a solution based on hierarchical transformers and l…

Image GenerationLanguage ModelingLanguage ModellingSuper-Resolution+2

CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

2022-05-29 · Wenyi Hong, Ming Ding, Wendi Zheng, Xinghan Liu 외

Large-scale pretrained transformers have created milestones in text (GPT-3) and text-to-image (DALL-E and CogView) generation. Its application to video generation is still facing many challenges: The potential huge compu…

Text-to-Video GenerationVideo Generation

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion

2024-03-08 · Wendi Zheng, Jiayan Teng, Zhuoyi Yang, Weihan Wang 외

Recent advancements in text-to-image generative systems have been largely driven by diffusion models. However, single-stage text-to-image diffusion models still face challenges, in terms of computational efficiency and t…

Computational EfficiencyImage GenerationSuper-ResolutionText to Image Generation+1

CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP

2022-03-01 · ZiHao Wang, Wei Liu, Qian He, Xinglong Wu 외

Training a text-to-image generator in the general domain (e.g., Dall.e, CogView) requires huge amounts of paired text-image data, which is too expensive to collect. In this paper, we propose a self-supervised scheme name…

Image GenerationText to Image GenerationText-to-Image Generation

Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

2024-10-14 · Xiangru Zhu, Penglei Sun, Yaoxian Song, Yanghua Xiao 외

Accurate interpretation and visualization of human instructions are crucial for text-to-image (T2I) synthesis. However, current models struggle to capture semantic variations from word order changes, and existing evaluat…

cross-modal alignmentImage Generation