Tag
MOSS 发布新的开源图像生成模型,拥有 5B 参数并采用 Apache 2.0 许可,支持通过 JSON 进行精确布局控制以及 4K token 的长提示词。
MOSS-Image is an open 5B diffusion transformer combining high-fidelity image synthesis with intent-aware prompt enhancement for bilingual long-form text rendering and layout-coherent generation, achieving state-of-the-art open-weight results on the new LongLongTextBench and RealLayoutArena benchmarks.
LIFT is a unified image-to-video generation framework that introduces layout-in-future control to specify future scene content and layout, improving quality and controllability under large viewpoint changes.
LooseControlVideo introduces a framework for intuitive 3D spatial control in text-to-video generation using sparse oriented 3D boxes as proxies, achieving superior trajectory accuracy and occlusion handling. It fine-tunes a Wan 2.2 backbone and demonstrates significant improvements over existing methods on multiple benchmarks.
Reve 2.0 is a product that enables generating and editing 4K images with layout-based control.
Ideogram 4.0 is released as an open-weight model with layout control for generating design-ready images.