Introducing Würstchen: Fast Diffusion for Image Generation

Efficient and Training-Free Single-Image Diffusion Models

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.

DiffusionGemma: 4x faster text generation

Consistency Models

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.

Advanced Image Generation: Negative Prompt Optimization and Latent Classifier Guidance

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.

Cost-Aware Routing for Efficient Text-To-Image Generation

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.

Video generation models as world simulators

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.