Video generation has witnessed significant advancements yet evaluating these models
remains a challenge. A comprehensive evaluation benchmark for video generation is …

Abstract This paper presents Instruct-Imagen a model that tackles heterogeneous image
generation tasks and generalizes across unseen tasks. We introduce multi-modal instruction …

Generative models can produce impressively realistic images. This paper demonstrates that
generated images have geometric features different from those of real images. We build a …

In an era where images and visual content dominate our digital landscape, the ability to
manipulate and personalize these images has become a necessity. Envision seamlessly …

Despite significant progress in generative AI, comprehensive evaluation remains
challenging because of the lack of effective metrics and standardized benchmarks. For …

We introduce LightIt a method for explicit illumination control for image generation. Recent
generative methods lack lighting control which is crucial to numerous artistic aspects of …

Video-to-video editing involves editing a source video along with additional control (such as
text prompts, subjects, or styles) to generate a new video that aligns with the source video …

In the rapidly advancing field of conditional image generation research, challenges such as
limited explainability lie in effectively evaluating the performance and capabilities of various …

Interleaved text-and-image generation has been an intriguing research direction, where the
models are required to generate both images and text pieces in an arbitrary order. Despite …

Despite progress in video-language modeling, the computational challenge of interpreting
long-form videos in response to task-specific linguistic queries persists, largely due to the …