Related papers: Text Embedding Knows How to Quantize Text-Guided D…
Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We…
Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained…
We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained…
The diffusion model has demonstrated superior performance in synthesizing diverse and high-quality images for text-guided image translation. However, there remains room for improvement in both the formulation of text prompts and the…
Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals often prevent these models from fully capturing specific…
Text-to-image generation has advanced rapidly, yet aligning complex textual prompts with generated visuals remains challenging, especially with intricate object relationships and fine-grained details. This paper introduces Fast Prompt…
Layer-wise PTQ is a promising technique for compressing large language models (LLMs), due to its simplicity and effectiveness without requiring retraining. However, recent progress in this area is saturating, underscoring the need to…
Generating images with embedded text is crucial for the automatic production of visual and multimodal documents, such as educational materials and advertisements. However, existing diffusion-based text-to-image models often struggle to…
Transferring large amount of high resolution images over limited bandwidth is an important but very challenging task. Compressing images using extremely low bitrates (<0.1 bpp) has been studied but it often results in low quality images of…
Diffusion models have become prominent in creating high-quality images. However, unlike GAN models celebrated for their ability to edit images in a disentangled manner, diffusion-based text-to-image models struggle to achieve the same level…
Diffusion models have made impressive progress in text-to-image synthesis. However, training such large-scale models (e.g. Stable Diffusion), from scratch requires high computational costs and massive high-quality text-image pairs, which…
Recent advancements in diffusion models, particularly the architectural transformation from UNet-based models to Diffusion Transformers (DiTs), significantly improve the quality and scalability of image and video generation. However,…
Text-to-image diffusion models are computationally intensive, often requiring dozens of forward passes through large transformer backbones. For instance, Stable Diffusion XL generates high-quality images with 50 evaluations of a…
Text-to-image diffusion models particularly Stable Diffusion, have revolutionized the field of computer vision. However, the synthesis quality often deteriorates when asked to generate images that faithfully represent complex prompts…
Diffusion models are the state of the art in text-to-image generation, but their perceptual variability remains understudied. In this paper, we examine how prompts affect image variability in black-box diffusion-based models. We propose…
Vision generative models have recently made significant advancements along two primary paradigms: diffusion-style and language-style, both of which have demonstrated excellent scaling laws. Quantization is crucial for efficiently deploying…
Text-to-image diffusion models generate images by iteratively denoising random noise, conditioned on a prompt. While these models have enabled impressive progress in image generation, they often fail to accurately reflect all semantic…
Text-to-image generation for personalized identities aims at incorporating the specific identity into images using a text prompt and an identity image. Based on the powerful generative capabilities of DDPMs, many previous works adopt…
Text-to-image generation is a significant domain in modern computer vision and has achieved substantial improvements through the evolution of generative architectures. Among these, there are diffusion-based models that have demonstrated…
Prompt tuning for vision-language models such as CLIP involves optimizing the text prompts used to generate image-text pairs for specific downstream tasks. While hand-crafted or template-based prompts are generally applicable to a wider…