Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think

• URL: http://arxiv.org/abs/2502.20172v1
• Date: Thu, 27 Feb 2025 15:08:39 GMT
• Title: Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think
• Authors: Liang Chen, Shuai Bai, Wenhao Chai, Weichu Xie, Haozhe Zhao, Leon Vinci, Junyang Lin, Baobao Chang,
• Abstract summary: We propose Dream Engine, an efficient framework designed for arbitrary text-image interleaved control in image generation models.<n>Our approach utilizes a two-stage training paradigm, consisting of joint text-image alignment and multimodal interleaved instruction tuning.<n>Our experiments demonstrate that this training method is effective, achieving a 0.69 overall score on the GenEval benchmark.
• Score: 38.258453761376586
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control output images with additional conditions, like canny and depth map, a comprehensive framework for arbitrary text-image interleaved control is still lacking. This gap is especially evident when attempting to merge concepts or visual elements from multiple images in the generation process. To mitigate the gap, we conducted preliminary experiments showing that large multimodal models (LMMs) offer an effective shared representation space, where image and text can be well-aligned to serve as a condition for external diffusion models. Based on this discovery, we propose Dream Engine, an efficient and unified framework designed for arbitrary text-image interleaved control in image generation models. Building on powerful text-to-image models like SD3.5, we replace the original text-only encoders by incorporating versatile multimodal information encoders such as QwenVL. Our approach utilizes a two-stage training paradigm, consisting of joint text-image alignment and multimodal interleaved instruction tuning. Our experiments demonstrate that this training method is effective, achieving a 0.69 overall score on the GenEval benchmark, and matching the performance of state-of-the-art text-to-image models like SD3.5 and FLUX.

Related papers

• UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion [36.06457895469353]
  UNIMO-G is a conditional diffusion framework that operates on multimodal prompts with interleaved textual and visual inputs. It excels in both text-to-image generation and zero-shot subject-driven synthesis.
  arXiv  Detail & Related papers  (2024-01-24T11:36:44Z)
• De-Diffusion Makes Text a Strong Cross-Modal Interface [33.90004746543745]
  We employ an autoencoder that uses a pre-trained text-to-image diffusion model for decoding. Experiments validate the precision and comprehensiveness of De-Diffusion text representing images. A single De-Diffusion model can generalize to provide transferable prompts for different text-to-image tools.
  arXiv  Detail & Related papers  (2023-11-01T16:12:40Z)
• Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning [115.50132185963139]
  CM3Leon is a decoder-only multi-modal language model capable of generating and infilling both text and images. It is the first multi-modal model trained with a recipe adapted from text-only language models. CM3Leon achieves state-of-the-art performance in text-to-image generation with 5x less training compute than comparable methods.
  arXiv  Detail & Related papers  (2023-09-05T21:27:27Z)
• Generating Images with Multimodal Language Models [78.6660334861137]
  We propose a method to fuse frozen text-only large language models with pre-trained image encoder and decoder models. Our model demonstrates a wide suite of multimodal capabilities: image retrieval, novel image generation, and multimodal dialogue.
  arXiv  Detail & Related papers  (2023-05-26T19:22:03Z)
• Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generation [63.061871048769596]
  We present a novel Unified Multi-Modal Latent Diffusion (UMM-Diffusion) which takes joint texts and images containing specified subjects as input sequences. To be more specific, both input texts and images are encoded into one unified multi-modal latent space. Our method is able to generate high-quality images with complex semantics from both aspects of input texts and images.
  arXiv  Detail & Related papers  (2023-03-16T13:50:20Z)
• 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)
• Towards Open-World Text-Guided Face Image Generation and Manipulation [52.83401421019309]
  We propose a unified framework for both face image generation and manipulation. Our method supports open-world scenarios, including both image and text, without any re-training, fine-tuning, or post-processing.
  arXiv  Detail & Related papers  (2021-04-18T16:56:07Z)
• TediGAN: Text-Guided Diverse Face Image Generation and Manipulation [52.83401421019309]
  TediGAN is a framework for multi-modal image generation and manipulation with textual descriptions. StyleGAN inversion module maps real images to the latent space of a well-trained StyleGAN. visual-linguistic similarity learns the text-image matching by mapping the image and text into a common embedding space. instance-level optimization is for identity preservation in manipulation.
  arXiv  Detail & Related papers  (2020-12-06T16:20:19Z)

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.