paper-with-me

Papers

TokenCompose: Text-to-Image Diffusion with Token-level Supervision

2023-12-06 · CVPR 2024 1 · ZiRui Wang, Zhizhou Sha, Zheng Ding, Yilin Wang, Zhuowen Tu

We present TokenCompose, a Latent Diffusion Model for text-to-image generation that achieves enhanced consistency between user-specified text prompts and model-generated images. Despite its tremendous success, the standard denoising process in the Latent Diffusion Model takes text prompts as conditions only, absent explicit constraint for the consistency between the text prompts and the image contents, leading to unsatisfactory results for composing multiple object categories. TokenCompose aims to improve multi-category instance composition by introducing the token-wise consistency terms between the image content and object segmentation maps in the finetuning stage. TokenCompose can be applied directly to the existing training pipeline of text-conditioned diffusion models without extra human labeling information. By finetuning Stable Diffusion, the model exhibits significant improvements in multi-category instance composition and enhanced photorealism for its generated images. Project link: https://mlpc-ucsd.github.io/TokenCompose

📄 PDF Abstract BibTeX arXiv:2312.03626

Code (1)

mlpc-ucsd/TokenCompose 공식 구현 pytorch

Tasks

DenoisingImage GenerationObjectText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Energy Based Process Energy Based Processes extend energy based models to exchangeable data while allowing neural network parameterizations of the energy function. They extend the previously…
EXP-$Does Expedia refund a cancelled flight? EXP-$Does Expedia refund a cancelled flight? If you’re wondering, +1 888-829-0881 does Expedia refund a cancelled flight, the answer depends+1 888-829-0881 on the airline’s…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.

Similar Papers 제목 키워드 기반

Causal Diffusion Transformers for Generative Modeling

2024-12-16 · Chaorui Deng, Deyao Zhu, Kunchang Li, Shi Guang 외

We introduce Causal Diffusion as the autoregressive (AR) counterpart of Diffusion models. It is a next-token(s) forecasting framework that is friendly to both discrete and continuous modalities and compatible with existi…

DecoderImage Generation

AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models

2025-09-29 · Bowei Chen, Sai Bi, Hao Tan, He Zhang 외 arxiv

In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasize…

Image Generation

CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models

2025-02-01 · Xinle Cheng, Zhuoming Chen, Zhihao Jia

Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we presen…

DenoisingImage Generation

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

2025-03-18 · Minglei Shi, Ziyang Yuan, Haotian Yang, Xintao Wang 외

Diffusion models have demonstrated remarkable success in various image generation tasks, but their performance is often limited by the uniform processing of inputs across varying conditions and noise levels. To address t…

Image GenerationText to Image GenerationText-to-Image Generation

Mixture of States: Routing Token-Level Dynamics for Multimodal Generation

2025-11-15 · Haozhe Liu, Ding Liu, Mingchen Zhuge, Zijian Zhou 외 arxiv

We introduce MoS (Mixture of States), a novel fusion paradigm for multimodal diffusion models that merges modalities using flexible, state-based interactions. The core of MoS is a learnable, token-wise router that create…

Text-to-Image Generationmultimodal generation