相关论文: Alchemist: Unlocking Efficiency in Text-to-Image M…

Contemporary Text-to-Image (T2I) models frequently depend on qualitative human evaluations to assess the consistency between synthesized images and the text prompts. There is a demand for quantitative and automatic evaluation tools, given…

Text-to-Image (T2I) models have recently achieved remarkable success in generating images from textual descriptions. However, challenges still persist in accurately rendering complex scenes where actions and interactions form the primary…

Instruction tuning is essential for Large Language Models (LLMs) to effectively follow user instructions. To improve training efficiency and reduce data redundancy, recent works use LLM-based scoring functions, e.g., Instruction-Following…

Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecified prompts, leading to suboptimal image-text alignment, aesthetics, and quality. We propose a…

Text-to-image diffusion models (T2I) have demonstrated unprecedented capabilities in creating realistic and aesthetic images. On the contrary, text-to-video diffusion models (T2V) still lag far behind in frame quality and text alignment,…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lacking compositionality could have severe implications for…

Despite the recent advances in personalized text-to-image (P-T2I) generative models, it remains challenging to perform finetuning-free multi-subject-driven T2I in a resource-efficient manner. Predominantly, contemporary approaches,…

Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts…

Deep learning (DL) is a powerful tool in computational imaging for many applications. A common strategy is to reconstruct a preliminary image as the input of a neural network to achieve an optimized image. Usually, the preliminary image is…

Text-to-image (T2I) models based on diffusion and transformer architectures advance rapidly. They are often pretrained on large corpora, and openly shared on a model platform, such as HuggingFace. Users can then build up AI applications,…

Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching between the few…

The rapid advancement of text-to-image (T2I) models has increased the need for reliable human preference modeling, a demand further amplified by recent progress in reinforcement learning for preference alignment. However, existing…

Text-to-image (T2I) personalization allows users to guide the creative image generation process by combining their own visual concepts in natural language prompts. Recently, encoder-based techniques have emerged as a new effective approach…

When humans read a specific text, they often visualize the corresponding images, and we hope that computers can do the same. Text-to-image synthesis (T2I), which focuses on generating high-quality images from textual descriptions, has…

Editing particle-system visual effects (VFX) is vital for digital storytelling, but achieving controllable, art-directable results remains challenging due to their multi-dimensional nature. Given a large collection of parameters, users must…

Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts. This paper introduces TextMatch, a novel framework that leverages multimodal optimization…

Integrating textual graphs into Large Language Models (LLMs) is promising for complex graph-based QA. However, a key bottleneck is retrieving informative yet compact subgraphs that fit the LLM context. Existing retrievers often struggle,…

Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inconsistency in web-scraped datasets, recent works shifted…

Text-to-Image (T2I) generation has made significant advancements with diffusion models, yet challenges persist in handling complex instructions, ensuring fine-grained content control, and maintaining deep semantic consistency. Existing T2I…