SVG-T2I：无需变分自编码器的文本到图像潜在扩散模型规模化研究

摘要

基于视觉基础模型（VFM）表征的视觉生成为融合视觉理解、感知与生成提供了一条极具前景的统一路径。尽管潜力巨大，但在VFM表征空间内完整训练大规模文生图扩散模型的研究仍属空白。为填补这一空白，我们扩展了SVG（自监督视觉生成表征）框架，提出SVG-T2I以直接在VFM特征域实现高质量文生图合成。通过采用标准文生图扩散流程，SVG-T2I取得了具有竞争力的性能：在GenEval上达到0.75分，在DPG-Bench上获得85.78分。这一性能验证了VFM在生成任务中固有的表征能力。我们已将项目完全开源，包括自动编码器与生成模型，及其训练、推理、评估流程与预训练权重，以推动表征驱动视觉生成的进一步研究。

English

Visual generation grounded in Visual Foundation Model (VFM) representations offers a highly promising unified pathway for integrating visual understanding, perception, and generation. Despite this potential, training large-scale text-to-image diffusion models entirely within the VFM representation space remains largely unexplored. To bridge this gap, we scale the SVG (Self-supervised representations for Visual Generation) framework, proposing SVG-T2I to support high-quality text-to-image synthesis directly in the VFM feature domain. By leveraging a standard text-to-image diffusion pipeline, SVG-T2I achieves competitive performance, reaching 0.75 on GenEval and 85.78 on DPG-Bench. This performance validates the intrinsic representational power of VFMs for generative tasks. We fully open-source the project, including the autoencoder and generation model, together with their training, inference, evaluation pipelines, and pre-trained weights, to facilitate further research in representation-driven visual generation.

SVG-T2I：无需变分自编码器的文本到图像潜在扩散模型规模化研究

SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder

摘要

Support