FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

FrameForge introduces a unified image generation framework that leverages pretrained video foundation models to capture dynamic temporal relationships between conditions and targets. It employs a Mixture of Temporal Experts (MoTE) to adaptively select temporal intervals and a Chain of Temporal Reasoning (CoTR) to model transformations through latent intermediate states, guided by a reasoning-bottleneck attention mask. Experiments on DreamBench, COCO2017, and GEdit-Bench demonstrate FrameForge’s superior performance in subject-driven generation, canny-to-image generation, and image editing compared to existing methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• diffusion