image latents
- LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process
- Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
- Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
- XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation