ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Lianghua, Wang, Wei, Wu, Zhi-Fan, Shi, Yupeng, Liang, Chen, Shen, Tong, Zhang, Han, Dou, Huanzhang, Liu, Yu, Zhou, Jingren
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912159714246656
author Huang, Lianghua
Wang, Wei
Wu, Zhi-Fan
Shi, Yupeng
Liang, Chen
Shen, Tong
Zhang, Han
Dou, Huanzhang
Liu, Yu
Zhou, Jingren
author_facet Huang, Lianghua
Wang, Wei
Wu, Zhi-Fan
Shi, Yupeng
Liang, Chen
Shen, Tong
Zhang, Han
Dou, Huanzhang
Liu, Yu
Zhou, Jingren
contents Recent research arXiv:2410.15027 arXiv:2410.23775 has highlighted the inherent in-context generation capabilities of pretrained diffusion transformers (DiTs), enabling them to seamlessly adapt to diverse visual tasks with minimal or no architectural modifications. These capabilities are unlocked by concatenating self-attention tokens across multiple input and target images, combined with grouped and masked generation pipelines. Building upon this foundation, we present ChatDiT, a zero-shot, general-purpose, and interactive visual generation framework that leverages pretrained diffusion transformers in their original form, requiring no additional tuning, adapters, or modifications. Users can interact with ChatDiT to create interleaved text-image articles, multi-page picture books, edit images, design IP derivatives, or develop character design settings, all through free-form natural language across one or more conversational rounds. At its core, ChatDiT employs a multi-agent system comprising three key components: an Instruction-Parsing agent that interprets user-uploaded images and instructions, a Strategy-Planning agent that devises single-step or multi-step generation actions, and an Execution agent that performs these actions using an in-context toolkit of diffusion transformers. We thoroughly evaluate ChatDiT on IDEA-Bench arXiv:2412.11767, comprising 100 real-world design tasks and 275 cases with diverse instructions and varying numbers of input and target images. Despite its simplicity and training-free approach, ChatDiT surpasses all competitors, including those specifically designed and trained on extensive multi-task datasets. We further identify key limitations of pretrained DiTs in zero-shot adapting to tasks. We release all code, agents, results, and intermediate outputs to facilitate further research at https://github.com/ali-vilab/ChatDiT
format Preprint
id arxiv_https___arxiv_org_abs_2412_12571
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers
Huang, Lianghua
Wang, Wei
Wu, Zhi-Fan
Shi, Yupeng
Liang, Chen
Shen, Tong
Zhang, Han
Dou, Huanzhang
Liu, Yu
Zhou, Jingren
Computer Vision and Pattern Recognition
Recent research arXiv:2410.15027 arXiv:2410.23775 has highlighted the inherent in-context generation capabilities of pretrained diffusion transformers (DiTs), enabling them to seamlessly adapt to diverse visual tasks with minimal or no architectural modifications. These capabilities are unlocked by concatenating self-attention tokens across multiple input and target images, combined with grouped and masked generation pipelines. Building upon this foundation, we present ChatDiT, a zero-shot, general-purpose, and interactive visual generation framework that leverages pretrained diffusion transformers in their original form, requiring no additional tuning, adapters, or modifications. Users can interact with ChatDiT to create interleaved text-image articles, multi-page picture books, edit images, design IP derivatives, or develop character design settings, all through free-form natural language across one or more conversational rounds. At its core, ChatDiT employs a multi-agent system comprising three key components: an Instruction-Parsing agent that interprets user-uploaded images and instructions, a Strategy-Planning agent that devises single-step or multi-step generation actions, and an Execution agent that performs these actions using an in-context toolkit of diffusion transformers. We thoroughly evaluate ChatDiT on IDEA-Bench arXiv:2412.11767, comprising 100 real-world design tasks and 275 cases with diverse instructions and varying numbers of input and target images. Despite its simplicity and training-free approach, ChatDiT surpasses all competitors, including those specifically designed and trained on extensive multi-task datasets. We further identify key limitations of pretrained DiTs in zero-shot adapting to tasks. We release all code, agents, results, and intermediate outputs to facilitate further research at https://github.com/ali-vilab/ChatDiT
title ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.12571