Related papers: ControlNet++: Improving Conditional Controls with …

In the e-commerce realm, compelling advertising images are pivotal for attracting customer attention. While generative models automate image generation, they often produce substandard images that may mislead customers and require…

Recent deep learning-based image denoising methods have shown impressive performance; however, many lack the flexibility to adjust the denoising strength based on the noise levels, camera settings, and user preferences. In this paper, we…

We present Compound Conditioned ControlNet, C3Net, a novel generative neural architecture taking conditions from multiple modalities and synthesizing multimodal contents simultaneously (e.g., image, text, audio). C3Net adapts the ControlNet…

Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability and controllability in real-world applications. To overcome…

Recent conditional image generation methods can improve controllability by generating images that are faithful to conditions such as sketches, human poses, segmentation maps, and depth. By applying these techniques to image augmentation…

We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in…

With the rapid advancement of vision generation models, the potential security risks stemming from synthetic visual content have garnered increasing attention, posing significant challenges for AI-generated image detection. Existing methods…

Conditional image synthesis based on user-specified requirements is a key component in creating complex visual content. In recent years, diffusion-based generative modeling has become a highly effective way for conditional image synthesis,…

In the dataset of image captioning, each image is aligned with several descriptions. Despite the fact that the quality of these descriptions varies, existing captioning models treat them equally in the training process. In this paper, we…

Recent strides in the development of diffusion models, exemplified by advancements such as Stable Diffusion, have underscored their remarkable prowess in generating visually compelling images. However, the imperative of achieving a seamless…

Text-to-image diffusion models exhibit remarkable generative capabilities, but lack precise control over object counts and spatial arrangements. This work introduces a two-stage system to address these compositional limitations. The first…

Recent advances in text-to-speech (TTS) have enabled natural speech synthesis, but fine-grained, time-varying emotion control remains challenging. Existing methods often allow only utterance-level control and require full model fine-tuning…

Diffusion models have emerged as powerful tools for generative tasks, producing high-quality outputs across diverse domains. However, how the generated data responds to the initial noise perturbation in diffusion models remains…

Fine-grained control of text-to-image diffusion transformer models (DiT) remains a critical challenge for practical deployment. While recent advances such as OminiControl and others have enabled a controllable generation of diverse control…

Denoising diffusion models have gained popularity as a generative modeling technique for producing high-quality and diverse images. Applying these models to downstream tasks requires conditioning, which can take the form of text, class…

While modern text-to-image diffusion models generate high-fidelity images, they offer limited control over the spatial and geometric structure of the output. To address this, we introduce and evaluate two ControlNets specialized for…

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-trained generative models to maximize a given reward function,…

Consistency models (CMs) are a powerful class of diffusion-based generative models optimized for fast sampling. Most existing CMs are trained using discretized timesteps, which introduce additional hyperparameters and are prone to…

Text-to-audio diffusion models produce high-quality and diverse music but many, if not most, of the SOTA models lack the fine-grained, time-varying controls essential for music production. ControlNet enables attaching external controls to a…

Segmentation of enhancement in LGE cardiac MRI is critical for diagnosing various ischemic and non-ischemic cardiomyopathies. However, creating pixel-level annotations for these images is challenging and labor-intensive, leading to limited…