Related papers: Flux Already Knows -- Activating Subject-Driven Im…

Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical…

3D asset generation is getting massive amounts of attention, inspired by the recent success of text-guided 2D content creation. Existing text-to-3D methods use pretrained text-to-image diffusion models in an optimization problem or…

The practical use of text-to-image generation has evolved from simple, monolithic models to complex workflows that combine multiple specialized components. While workflow-based approaches can lead to improved image quality, crafting…

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…

Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by generating either…

We propose to use automatically generated instruction-following data to improve the zero-shot capabilities of a large multimodal model with additional support for generative and image editing tasks. We achieve this by curating a new…

Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g., a woman's photo) and a text description (e.g., "a woman is drinking water."). Existing TI2V frameworks often require…

There is a growing interest in dataset generation recently due to the superior generative capacity of large pre-trained language models (PLMs). In this paper, we study a flexible and efficient zero-short learning method, \textsc{ZeroGen}.…

Research in vision-language models has seen rapid developments off-late, enabling natural language-based interfaces for image generation and manipulation. Many existing text guided manipulation techniques are restricted to specific classes…

Knowledge distillation has made remarkable achievements in model compression. However, most existing methods require the original training data, which is usually unavailable due to privacy and security issues. In this paper, we propose a…

Personalized image generation with text-to-image diffusion models generates unseen images based on reference image content. Zero-shot adapter methods such as IP-Adapter and OminiControl are especially interesting because they do not require…

Recent advances in text-to-image diffusion models have substantially improved the quality of image customization, enabling the synthesis of highly realistic images. Despite this progress, achieving fast and efficient personalization remains…

The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…

We present SUGAR, a zero-shot method for subject-driven video customization. Given an input image, SUGAR is capable of generating videos for the subject contained in the image and aligning the generation with arbitrary visual attributes…

Real-world image recognition systems need to recognize tens of thousands of classes that constitute a plethora of visual concepts. The traditional approach of annotating thousands of images per class for training is infeasible in such a…

Zero-shot learning (ZSL) makes object recognition in images possible in absence of visual training data for a part of the classes from a dataset. When the number of classes is large, classes are usually represented by semantic class…

Diffusion models have recently been employed to generate high-quality images, reducing the need for manual data collection and improving model generalization in tasks such as object detection, instance segmentation, and image perception.…

This paper explores the feasibility of using text-to-image models in a zero-shot setup to generate images for taxonomy concepts. While text-based methods for taxonomy enrichment are well-established, the potential of the visual dimension…

Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior…

This work investigates the use of natural language to enable zero-shot model adaptation to new tasks. We use text and metadata from social commenting platforms as a source for a simple pretraining task. We then provide the language model…