Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

• URL: http://arxiv.org/abs/2408.02657v1
• Date: Mon, 5 Aug 2024 17:46:53 GMT
• Title: Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining
• Authors: Dongyang Liu, Shitian Zhao, Le Zhuo, Weifeng Lin, Yu Qiao, Hongsheng Li, Peng Gao,
• Abstract summary: Lumina-mGPT is a family of multimodal autoregressive models capable of various vision and language tasks. We introduce Ominiponent Supervised Finetuning, transforming Lumina-mGPT into a foundation model that seamlessly achieves omnipotent task unification.
• Score: 48.98105914356609
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present Lumina-mGPT, a family of multimodal autoregressive models capable of various vision and language tasks, particularly excelling in generating flexible photorealistic images from text descriptions. Unlike existing autoregressive image generation approaches, Lumina-mGPT employs a pretrained decoder-only transformer as a unified framework for modeling multimodal token sequences. Our key insight is that a simple decoder-only transformer with multimodal Generative PreTraining (mGPT), utilizing the next-token prediction objective on massive interleaved text-image sequences, can learn broad and general multimodal capabilities, thereby illuminating photorealistic text-to-image generation. Building on these pretrained models, we propose Flexible Progressive Supervised Finetuning (FP-SFT) on high-quality image-text pairs to fully unlock their potential for high-aesthetic image synthesis at any resolution while maintaining their general multimodal capabilities. Furthermore, we introduce Ominiponent Supervised Finetuning (Omni-SFT), transforming Lumina-mGPT into a foundation model that seamlessly achieves omnipotent task unification. The resulting model demonstrates versatile multimodal capabilities, including visual generation tasks like flexible text-to-image generation and controllable generation, visual recognition tasks like segmentation and depth estimation, and vision-language tasks like multiturn visual question answering. Additionally, we analyze the differences and similarities between diffusion-based and autoregressive methods in a direct comparison.

Related papers

• From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities [31.108694010274988]
  We introduce a novel image tokenizer that bridges this gap by applying the principle of Byte-Pair. Our method directly incorporates structural prior information into image tokens, mirroring the successful tokenization strategies used in text-only Large Language Models.
  arXiv  Detail & Related papers  (2024-10-03T02:34:31Z)
• MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model [49.931663904599205]
  MaVEn is an innovative framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. We show that MaVEn significantly enhances MLLMs' understanding in complex multi-image scenarios, while also improving performance in single-image contexts.
  arXiv  Detail & Related papers  (2024-08-22T11:57:16Z)
• A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models [7.350203999073509]
  Feature Guidance Attack (FGA) is a novel method that uses text representations to direct the perturbation of clean images. Our method demonstrates stable and effective attack capabilities across various datasets, downstream tasks, and both black-box and white-box settings.
  arXiv  Detail & Related papers  (2024-07-25T06:10:33Z)
• VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation [79.02357561313785]
  We introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for both image and text modalities by employing a straightforward auto-regressive objective.
  arXiv  Detail & Related papers  (2023-12-14T18:59:43Z)
• Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization [52.935150075484074]
  We introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language. The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image. This unification empowers LaVIT to serve as an impressive generalist interface to understand and generate multi-modal content simultaneously.
  arXiv  Detail & Related papers  (2023-09-09T03:01:38Z)
• MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models [12.397136690734865]
  We propose a novel approach called Multi-modal Deep-symphysis Prompt Tuning, dubbed as MuDPT. MuDPT extends independent multi-modal prompt tuning by learning a model-agnostic transformative network to allow deep hierarchical bi-directional prompt fusion. Compared with the state-of-the-art methods, MuDPT achieves better recognition and generalization ability with an apparent margin.
  arXiv  Detail & Related papers  (2023-06-20T09:15:52Z)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)
• GPT4Image: Can Large Pre-trained Models Help Vision Models on Perception Tasks? [51.22096780511165]
  We present a new learning paradigm in which the knowledge extracted from large pre-trained models are utilized to help models like CNN and ViT learn enhanced representations. We feed detailed descriptions into a pre-trained encoder to extract text embeddings with rich semantic information that encodes the content of images.
  arXiv  Detail & Related papers  (2023-06-01T14:02:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.