Related papers: A 28.6 mJ/iter Stable Diffusion Processor for Text…
Diffusion models are the go-to method for Text-to-Image generation, but their iterative denoising processes has high inference latency. Quantization reduces compute time by using lower bitwidths, but applies a fixed precision across all…
We introduce the Fixed Point Diffusion Model (FPDM), a novel approach to image generation that integrates the concept of fixed point solving into the framework of diffusion-based generative modeling. Our approach embeds an implicit fixed…
Recently, text-to-image models have been thriving. Despite their powerful generative capacity, our research has uncovered a lack of robustness in this generation process. Specifically, the introduction of small perturbations to the text…
Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we…
Diffusion models have achieved great success in synthesizing high-quality images. However, generating high-resolution images with diffusion models is still challenging due to the enormous computational costs, resulting in a prohibitive…
This paper proposes a high-performance and energy-efficient optical near-sensor accelerator for vision applications, called Lightator. Harnessing the promising efficiency offered by photonic devices, Lightator features innovative…
While text-driven diffusion models demonstrate remarkable performance in image editing, the critical components of their text embeddings remain underexplored. The ambiguity and entanglement of these embeddings pose challenges for precise…
Diffusion Probabilistic Models (DPMs) have emerged as the de facto approach for high-fidelity image synthesis, operating diffusion processes on continuous VAE latent, which significantly differ from the text generation methods employed by…
Text-to-image diffusion models are well-known for their ability to generate realistic images based on textual prompts. However, the existing works have predominantly focused on English, lacking support for non-English text-to-image models.…
Recently, zero-shot image captioning has gained increasing attention, where only text data is available for training. The remarkable progress in text-to-image diffusion model presents the potential to resolve this task by employing…
Large text-to-image diffusion models have impressive capabilities in generating photorealistic images from text prompts. How to effectively guide or control these powerful models to perform different downstream tasks becomes an important…
Stable Diffusion is a popular Transformer-based model for image generation from text; it applies an image information creator to the input text and the visual knowledge is added in a step-by-step fashion to create an image that corresponds…
While diffusion models significantly improve the perceptual quality of super-resolved images, they usually require a large number of sampling steps, resulting in high computational costs and long inference times. Recent efforts have…
Latent diffusion models have become the popular choice for scaling up diffusion models for high resolution image synthesis. Compared to pixel-space models that are trained end-to-end, latent models are perceived to be more efficient and to…
Tuning the parameters and prompts for improving AI-based text-to-image generation has remained a substantial yet unaddressed challenge. Hence we introduce GreenStableYolo, which improves the parameters and prompts for Stable Diffusion to…
Current large-scale generative models have impressive efficiency in generating high-quality images based on text prompts. However, they lack the ability to precisely control the size and position of objects in the generated image. In this…
We introduce TurboDiffusion, a video generation acceleration framework that can speed up end-to-end diffusion generation by 100-200x while maintaining video quality. TurboDiffusion mainly relies on several components for acceleration: (1)…
Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considerable computational resources for each query, making them…
Current large-scale diffusion models represent a giant leap forward in conditional image synthesis, capable of interpreting diverse cues like text, human poses, and edges. However, their reliance on substantial computational resources and…
Generative diffusion models have achieved remarkable success in producing high-quality images. However, these models typically operate in continuous intensity spaces, diffusing independently across pixels and color channels. As a result,…