Keywords: Text-to-Image Diffusion Model, Consistency Model
TL;DR: This paper introduces PIXART-δ, a text-to-image synthesis framework that integrates the Latent Consistency Model (LCM) and ControlNet into the advanced PIXART-α model.
Abstract: This paper introduces PIXART-δ, a text-to-image synthesis framework that integrates the Latent Consistency Model (LCM) and ControlNet into the advanced PIXART-α model. PIXART-α is recognized for its ability to generate high-quality images of 1024px resolution through a remarkably efficient training process. The integration of LCM in PIXART-δ significantly accelerates the inference speed, enabling the production of high-quality images in just 2-4 steps. Notably, PIXART-δ achieves a breakthrough of 0.5 seconds for generating 1024 × 1024 pixel images, marking a 7× improvement over the PIXART-α. Additionally, PIXART-δ is designed to be efficiently trainable on 32GB V100 GPUs within a single day. With its 8-bit inference capability, PIXART-δ can synthesize 1024px images within 8GB GPU memory constraints, greatly enhancing its usability and accessibility. Furthermore, incorporating a ControlNet-like module enables fine-grained control over text-to-image diffusion models. We introduce a novel ControlNet-Transformer architecture, specifically tailored for Transformers, achieving explicit controllability alongside high-quality image generation. As a state-of-the-art, open-source image generation model, PIXART-δ offers a promising alternative to the Stable Diffusion family of models, contributing significantly to text-to-image synthesis.
Submission Number: 1
Loading