Contextualized Diffusion Models for Text-Guided Image and Video Generation

• URL: http://arxiv.org/abs/2402.16627v3
• Date: Tue, 4 Jun 2024 01:08:56 GMT
• Title: Contextualized Diffusion Models for Text-Guided Image and Video Generation
• Authors: Ling Yang, Zhilong Zhang, Zhaochen Yu, Jingwei Liu, Minkai Xu, Stefano Ermon, Bin Cui,
• Abstract summary: Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. We propose a novel and general contextualized diffusion model (ContextDiff) by incorporating the cross-modal context encompassing interactions and alignments between text condition and visual sample. We generalize our model to both DDPMs and DDIMs with theoretical derivations, and demonstrate the effectiveness of our model in evaluations with two challenging tasks: text-to-image generation, and text-to-video editing.
• Score: 67.69171154637172
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. Nevertheless, prevailing text-guided visual diffusion models primarily focus on incorporating text-visual relationships exclusively into the reverse process, often disregarding their relevance in the forward process. This inconsistency between forward and reverse processes may limit the precise conveyance of textual semantics in visual synthesis results. To address this issue, we propose a novel and general contextualized diffusion model (ContextDiff) by incorporating the cross-modal context encompassing interactions and alignments between text condition and visual sample into forward and reverse processes. We propagate this context to all timesteps in the two processes to adapt their trajectories, thereby facilitating cross-modal conditional modeling. We generalize our contextualized diffusion to both DDPMs and DDIMs with theoretical derivations, and demonstrate the effectiveness of our model in evaluations with two challenging tasks: text-to-image generation, and text-to-video editing. In each task, our ContextDiff achieves new state-of-the-art performance, significantly enhancing the semantic alignment between text condition and generated samples, as evidenced by quantitative and qualitative evaluations. Our code is available at https://github.com/YangLing0818/ContextDiff

Related papers

• ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models [52.23899502520261]
  We introduce a new framework named ARTIST to focus on the learning of text structures. We finetune a visual diffusion model, enabling it to assimilate textual structure information from the pretrained textual model. Empirical results on the MARIO-Eval benchmark underscore the effectiveness of the proposed method, showing an improvement of up to 15% in various metrics.
  arXiv  Detail & Related papers  (2024-06-17T19:31:24Z)
• Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering [118.53208190209517]
  We propose a framework to learn the proper textual descriptions for diffusion models through prompt learning. Our method can effectively learn the prompts to improve the matches between the input text and the generated images.
  arXiv  Detail & Related papers  (2024-01-12T03:46:29Z)
• UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models [25.219960711604728]
  This paper proposes a novel approach for text image generation, utilizing a pre-trained diffusion model. Our approach involves the design and training of a light-weight character-level text encoder, which replaces the original CLIP encoder. By employing an inference stage refinement process, we achieve a notably high sequence accuracy when synthesizing text in arbitrarily given images.
  arXiv  Detail & Related papers  (2023-12-08T07:47:46Z)
• RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment [112.45442468794658]
  We propose a two-stage coarse-to-fine semantic re-alignment method, named RealignDiff. In the coarse semantic re-alignment phase, a novel caption reward is proposed to evaluate the semantic discrepancy between the generated image caption and the given text prompt. The fine semantic re-alignment stage employs a local dense caption generation module and a re-weighting attention modulation module to refine the previously generated images from a local semantic view.
  arXiv  Detail & Related papers  (2023-05-31T06:59:21Z)
• eDiffi: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers [87.52504764677226]
  Large-scale diffusion-based generative models have led to breakthroughs in text-conditioned high-resolution image synthesis. We train an ensemble of text-to-image diffusion models specialized for different stages synthesis. Our ensemble of diffusion models, called eDiffi, results in improved text alignment while maintaining the same inference cost.
  arXiv  Detail & Related papers  (2022-11-02T17:43:04Z)
• Improving Generation and Evaluation of Visual Stories via Semantic Consistency [72.00815192668193]
  Given a series of natural language captions, an agent must generate a sequence of images that correspond to the captions. Prior work has introduced recurrent generative models which outperform synthesis text-to-image models on this task. We present a number of improvements to prior modeling approaches, including the addition of a dual learning framework.
  arXiv  Detail & Related papers  (2021-05-20T20:42:42Z)
• The Devil is in the Details: Evaluating Limitations of Transformer-based Methods for Granular Tasks [19.099852869845495]
  Contextual embeddings derived from transformer-based neural language models have shown state-of-the-art performance for various tasks. We focus on the problem of textual similarity from two perspectives: matching documents on a granular level, and an abstract level. We empirically demonstrate, across two datasets from different domains, that despite high performance in abstract document matching as expected, contextual embeddings are consistently (and at times, vastly) outperformed by simple baselines like TF-IDF for more granular tasks.
  arXiv  Detail & Related papers  (2020-11-02T18:41:32Z)

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.