SVG-T2I：無需變分自編碼器的文字生成圖像潛在擴散模型規模化研究

摘要

基於視覺基礎模型（VFM）表徵的視覺生成，為整合視覺理解、感知與生成提供了一條極具前景的統一途徑。儘管存在此潛力，在VFM表徵空間內完全訓練大規模文生圖擴散模型的研究仍屬空白。為填補此缺口，我們擴展了SVG（自監督視覺生成表徵）框架，提出SVG-T2I以直接在VFM特徵域中實現高質量文生圖合成。通過採用標準文生圖擴散流程，SVG-T2I達到了可媲美現有技術的性能，在GenEval上獲得0.75分，在DPG-Bench上取得85.78分。此性能驗證了VFM表徵在生成任務中的內在潛力。我們將項目完整開源，包含自動編碼器與生成模型，以及其訓練、推理、評估流程和預訓練權重，以促進表徵驅動視覺生成的後續研究。

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：無需變分自編碼器的文字生成圖像潛在擴散模型規模化研究

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

摘要

Support