arXiv:2606. 04299v1 Announce Type: cross Abstract: We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image.
Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation.
arXiv:2607. 14580v1 Announce Type: cross Abstract: We present a novel system that integrates negative prompt optimization via a fine-tuned sequence-to-sequence LLM and latent-space classifier guidance to improve the quality of images generated by Stable Diffusion.
arXiv:2506. 14753v3 Announce Type: replace-cross Abstract: Diffusion models are well known for their ability to generate a high-fidelity image for an input prompt through an iterative denoising process.
We explore large-scale training of generative models on video data. Specifically, we train text-conditional diffusion models jointly on videos and images of variable durations, resolutions and aspect ratios.
arXiv:2606. 00094v1 Announce Type: cross Abstract: Image generative models aim to sample data points from the underlying data manifold, a task that requires learning and decoding a dense, low-dimensional, and compact parameterization space.
arXiv:2509. 24710v2 Announce Type: replace-cross Abstract: Score-based diffusion models are a highly effective method for generating samples from a distribution of images.
arXiv:2605. 07971v2 Announce Type: replace-cross Abstract: We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) based 3D generative pipelines.
The paper "Iterative Flow Matching: Path Correction and Gradual Refinement for Enhanced Generative Modeling" investigates the use of flow matching for image generation and identifies that this approach can produce hallucinations—unrealistic images. It proposes an iterative refinement process that can be incorporated into virtually any generative modeling technique to improve performance and robustness. The authors demonstrate how their method corrects the generation path and gradually refines outputs to mitigate hallucinations.