svg-t2i-vfm-diffusion

【效率与协作】Train text-to-image diffusion models directly in frozen DINOv3 feature spaces, eliminating VAE-based compression. Enables high-resolution synthesis by leveraging VFM representations as native latent manifolds with unified cross-modal transformers.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准