Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion
Summary
Block3D accelerates text-to-3D generation by using block-wise diffusion with confidence-guided correction to reduce inference time while preserving geometric fidelity, achieving a 5.15x speedup.
View Cached Full Text
Cached at: 08/25/26, 08:35 AM
Paper page - Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion
Source: https://huggingface.co/papers/2608.19567
Abstract
Block3D accelerates text-to-3D generation by using block-wise diffusion with confidence-guided correction to reduce inference time while preserving geometric fidelity.
Whiletext-to-3D generationhas advanced rapidly, achieving high geometric fidelity at low inference cost remains challenging. Existing text-to-3D methods either decodediscrete shape tokensautoregressively or iteratively refine global 3D representations with diffusion or flow models. However,autoregressive decodingis sequential and cannot revise errors, whereas diffusion andflow-matchingmodels repeatedly process the full representation, making high-quality generation increasingly expensive. In this paper, we propose Block3D, ablock-wise diffusionframework that partitions the discrete shape-token sequence into contiguous blocks, generates the blocks autoregressively, and jointly denoises all tokens within the current block. To alleviate error accumulation, we introduceconfidence-guided intra-block correction, which revises low-confidence tokens before each block is finalized. On a held-out set from TRELLIS-500K, Block3D reduces mean end-to-end generation time from 25.71 seconds to 4.99 seconds, achieving a 5.15times speedup over the fine-tuned autoregressive baseline without sacrificing geometric fidelity.
View arXiv pageView PDFProject pageGitHub3Add to collection
Get this paper in your agent:
hf papers read 2608\.19567
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.19567 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.19567 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.19567 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
DiffusionGemma: 4x Faster Text Generation
Google introduces DiffusionGemma, an experimental 26B MoE open model that achieves up to 4x faster text generation on GPUs using text diffusion, targeting speed-critical interactive local workflows.
I'm eager for a 15x speedup on my strix halo
Nvidia claims a 15x speedup in text generation using a diffusion model, generating entire blocks at once.
Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models
Flash-BoN improves text-to-image generation efficiency by generating cheap draft candidates via timestep truncation, layer skipping, and activation proxies, then using multi-stage verification to select the best draft for full refinement, outperforming baselines under fixed wall-clock budgets.
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Hunyuan3D 2.0 is a scalable flow-based diffusion transformer system for high-resolution textured 3D asset generation, outperforming state-of-the-art models and publicly released with code and weights.
Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models
NVIDIA introduces Nemotron-Labs Diffusion, a family of diffusion language models that generate text in parallel and iteratively refine it, offering faster generation and the ability to revise previous tokens.