DreamLCM: Towards High-Quality Text-to-3D Generation via Latent Consistency Model

TL;DR

DreamLCM introduces a novel approach for high-quality text-to-3D generation by leveraging a latent consistency model and innovative guidance strategies, significantly improving detail and convergence speed over previous methods.

Contribution

The paper proposes DreamLCM, integrating the Latent Consistency Model with guidance calibration and dual timestep strategies for superior 3D generation quality and efficiency.

Findings

Achieves state-of-the-art quality in text-to-3D generation.

Improves training efficiency compared to existing methods.

Provides detailed and consistent 3D models from text prompts.

Abstract

Recently, the text-to-3D task has developed rapidly due to the appearance of the SDS method. However, the SDS method always generates 3D objects with poor quality due to the over-smooth issue. This issue is attributed to two factors: 1) the DDPM single-step inference produces poor guidance gradients; 2) the randomness from the input noises and timesteps averages the details of the 3D contents. In this paper, to address the issue, we propose DreamLCM which incorporates the Latent Consistency Model (LCM). DreamLCM leverages the powerful image generation capabilities inherent in LCM, enabling generating consistent and high-quality guidance, i.e., predicted noises or images. Powered by the improved guidance, the proposed method can provide accurate and detailed gradients to optimize the target 3D models. In addition, we propose two strategies to enhance the generation quality further. Firstly, we propose a guidance calibration strategy, utilizing Euler Solver to calibrate the guidance distribution to accelerate 3D models to converge. Secondly, we propose a dual timestep strategy, increasing the consistency of guidance and optimizing 3D models from geometry to appearance in DreamLCM. Experiments show that DreamLCM achieves state-of-the-art results in both generation quality and training efficiency. The code is available at https://github.com/1YimingZhong/DreamLCM.