Related papers: MagicMix: Semantic Mixing with Diffusion Models
Diffusion models have shown great promise in synthesizing visually appealing images. However, it remains challenging to condition the synthesis at a fine-grained level, for instance, synthesizing image pixels following some generic color…
In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts. It hypothesizes that for objects with similar appearance, they share similar representation. Our method establishes dependencies…
Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images. Unlike existing methods that directly insert objects into the background, adaptive and interactive fusion…
Diffusion models have been shown to be capable of generating high-quality images, suggesting that they could contain meaningful internal representations. Unfortunately, the feature maps that encode a diffusion model's internal information…
The diffusion-based text-to-image model harbors immense potential in transferring reference style. However, current encoder-based approaches significantly impair the text controllability of text-to-image models while transferring styles. In…
Recent DiT-based text-to-image models increasingly adopt LLMs as text encoders, yet text conditioning remains largely static and often utilizes only a single LLM layer, despite pronounced semantic hierarchy across LLM layers and…
Match-cuts are powerful cinematic tools that create seamless transitions between scenes, delivering strong visual and metaphorical connections. However, crafting match-cuts is a challenging, resource-intensive process requiring deliberate…
Many visual scenes can be described as compositions of latent factors. Effective recognition, reasoning, and editing often require not only forming such compositional representations, but also solving the decomposition problem. One popular…
We are witnessing a revolution in conditional image synthesis with the recent success of large scale text-to-image generation methods. This success also opens up new opportunities in controlling the generation and editing process using…
Subject-driven image inpainting has recently gained prominence in image editing with the rapid advancement of diffusion models. Beyond image guidance, recent studies have explored incorporating text guidance to achieve identity-preserved…
Deep architecture have proven capable of solving many tasks provided a sufficient amount of labeled data. In fact, the amount of available labeled data has become the principal bottleneck in low label settings such as Semi-Supervised…
Addressing the limitations of text as a source of accurate layout representation in text-conditional diffusion models, many works incorporate additional signals to condition certain attributes within a generated image. Although successful,…
Diffusion models have demonstrated strong potential in language modeling, offering various advantages over traditional autoregressive approaches. Their ability to generate and revise entire responses in parallel enables faster generation…
Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation, which transfers knowledge from a complex teacher to a…
Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creation, virtual reality and visual media. Existing methods…
Recent advances in text-to-image diffusion models have achieved remarkable success in generating high-quality, realistic images from textual descriptions. However, these approaches have faced challenges in precisely aligning the generated…
The colorization of grayscale images is a complex and subjective task with significant challenges. Despite recent progress in employing large-scale datasets with deep neural networks, difficulties with controllability and visual quality…
Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding. Current methods either struggle with perceptual quality or suffer from significant distortion.…
Automatic font generation is an imitation task, which aims to create a font library that mimics the style of reference images while preserving the content from source images. Although existing font generation methods have achieved…
Synthesizing visually impressive images that seamlessly align both text prompts and specific artistic styles remains a significant challenge in Text-to-Image (T2I) diffusion models. This paper introduces StyleBlend, a method designed to…