Pixel-Space Diffusion Transformers
PulseAugur coverage of Pixel-Space Diffusion Transformers — every cluster mentioning Pixel-Space Diffusion Transformers across labs, papers, and developer communities, ranked by signal.
-
New methods PixelDense and Persistence Forcing boost diffusion model performance
Researchers have developed two novel techniques to enhance pixel-space diffusion models. PixelDense improves training by aligning semantic and geometric features separately, leading to better performance on tasks like i…
-
New methods enhance multimodal control in Diffusion Transformers for image generation
Researchers have developed new methods to enhance control over image generation using Diffusion Transformers (DiTs). One approach, 'Appearance Pointers,' uses compact tokens to guide DiTs for precise regional control ov…
-
Register tokens improve pixel-space Diffusion Transformers, research finds
Researchers have investigated the utility of register tokens in Diffusion Transformers (DiTs), drawing parallels to their effectiveness in Vision Transformers (ViTs). While ViTs benefit from register tokens by mitigatin…