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

arXiv: https://arxiv.org/abs/2408.02993 · HTML: https://mlsanity.com/paper/2408.02993/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 2 of its 3 references that are in the map.
- First posted on arXiv 6 Aug 2024.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 2 of 2)

- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)

## Built on by (most cited first, 8 of 8)

- [VistaDream: Sampling multiview consistent images for single-view scene reconstruction](https://mlsanity.com/paper/2410.16892/) (2024)
- [TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt](https://mlsanity.com/paper/2410.21299/) (2024)
- [CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting](https://mlsanity.com/paper/2412.19142/) (2024)
- [InstaFace: Identity-Preserving Facial Editing with Single Image Inference](https://mlsanity.com/paper/2502.20577/) (2025)
- [AvatarMakeup: Realistic Makeup Transfer for 3D Animatable Head Avatars](https://mlsanity.com/paper/2507.02419/) (2025)
- [Bridging Geometry-Coherent Text-to-3D Generation with Multi-View Diffusion Priors and Gaussian Splatting](https://mlsanity.com/paper/2505.04262/) (2025)
- [AvatarBack: Back-Head Generation for Complete 3D Avatars from Front-View Images](https://mlsanity.com/paper/2508.20623/) (2025)
- [CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation](https://mlsanity.com/paper/2605.20872/) (2026)

## Abstract (arXiv)

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.