Trae

ByteDance released Bernini-R, an open-source video generation and editing model that combines an MLLM-based semantic planner with a DiT-based renderer. The model requires Hopper-class GPUs (H100/H800/H200) for optimal performance and supports multiple tasks including text-to-video, video editing, and reference-guided generation.

ByteDance has released Lance, a 3-billion parameter multimodal model that performs image and video generation, editing, and understanding within a single framework. The model was trained entirely from scratch using 128 A100 GPUs and achieves 84.67% on DPG-Bench and 74% on GenEval, competing with larger models despite its compact size.

ByteDance confirmed Thursday that Dreamina Seedance 2.0, its audio and video generation model, is rolling out in CapCut across seven initial markets. The model generates videos up to 15 seconds with realistic textures and motion, but includes safety restrictions blocking generation from real faces and unauthorized IP use.

ByteDance has suspended the global rollout of Seedance 2.0, its AI video generator, according to The Information. The pause follows cease-and-desist letters from Disney and Paramount Skydance alleging the model was trained on copyrighted materials.

ByteDance has released Helios, a 14-billion-parameter open-weight video generation model that achieves 19.5 frames per second on a single GPU while generating minute-long video clips. The researchers claim this is the first model of its scale to reach near-real-time performance at this duration. Code and model weights are publicly available.

A new Bytedance study reveals that large reasoning models actually know when they've reached the correct answer, but common sampling methods prevent them from stopping. The models engage in unnecessary cross-checking and reformulation despite already solving problems correctly.