TextCraftor: Your Text Encoder Can be Image Quality Controller

• URL: http://arxiv.org/abs/2403.18978v1
• Date: Wed, 27 Mar 2024 19:52:55 GMT
• Title: TextCraftor: Your Text Encoder Can be Image Quality Controller
• Authors: Yanyu Li, Xian Liu, Anil Kag, Ju Hu, Yerlan Idelbayev, Dhritiman Sagar, Yanzhi Wang, Sergey Tulyakov, Jian Ren,
• Abstract summary: Diffusion-based text-to-image generative models, e.g., Stable Diffusion, have revolutionized the field of content generation. We propose a proposed fine-tuning approach, TextCraftor, to enhance the performance of text-to-image diffusion models.
• Score: 65.27457900325462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion-based text-to-image generative models, e.g., Stable Diffusion, have revolutionized the field of content generation, enabling significant advancements in areas like image editing and video synthesis. Despite their formidable capabilities, these models are not without their limitations. It is still challenging to synthesize an image that aligns well with the input text, and multiple runs with carefully crafted prompts are required to achieve satisfactory results. To mitigate these limitations, numerous studies have endeavored to fine-tune the pre-trained diffusion models, i.e., UNet, utilizing various technologies. Yet, amidst these efforts, a pivotal question of text-to-image diffusion model training has remained largely unexplored: Is it possible and feasible to fine-tune the text encoder to improve the performance of text-to-image diffusion models? Our findings reveal that, instead of replacing the CLIP text encoder used in Stable Diffusion with other large language models, we can enhance it through our proposed fine-tuning approach, TextCraftor, leading to substantial improvements in quantitative benchmarks and human assessments. Interestingly, our technique also empowers controllable image generation through the interpolation of different text encoders fine-tuned with various rewards. We also demonstrate that TextCraftor is orthogonal to UNet finetuning, and can be combined to further improve generative quality.

Related papers

• Conditional Text-to-Image Generation with Reference Guidance [81.99538302576302]
  This paper explores using additional conditions of an image that provides visual guidance of the particular subjects for diffusion models to generate. We develop several small-scale expert plugins that efficiently endow a Stable Diffusion model with the capability to take different references. Our expert plugins demonstrate superior results than the existing methods on all tasks, each containing only 28.55M trainable parameters.
  arXiv  Detail & Related papers  (2024-11-22T21:38:51Z)
• 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)
• 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)
• Enhancing Diffusion Models with Text-Encoder Reinforcement Learning [63.41513909279474]
  Text-to-image diffusion models are typically trained to optimize the log-likelihood objective. Recent research addresses this issue by refining the diffusion U-Net using human rewards through reinforcement learning or direct backpropagation. We demonstrate that by finetuning the text encoder through reinforcement learning, we can enhance the text-image alignment of the results.
  arXiv  Detail & Related papers  (2023-11-27T09:39:45Z)
• 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)
• 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)

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.