Wan2.1-T2V-1.3B
PulseAugur coverage of Wan2.1-T2V-1.3B — every cluster mentioning Wan2.1-T2V-1.3B across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Tsinghua and HKUST unveil real-time streaming video editor LiveEdit
Researchers from Tsinghua University and the Hong Kong University of Science and Technology have developed LiveEdit, a real-time streaming video editing framework. This system processes continuous video input in chunks,…
-
DUET model reconciles quality and diversity in video generation
Researchers have developed DUET, a novel two-step video generation method that combines trajectory-level and distribution-level distillation techniques. DUET utilizes two specialized experts: one for high-noise stages t…
-
DUET model reconciles quality and diversity in video generation
Researchers have introduced DUET, a novel approach to video generation using diffusion models that aims to overcome the quality-diversity trade-off inherent in current few-step distillation methods. DUET employs a two-e…
-
CachedSearch accelerates video diffusion model search with novel caching
Researchers have developed CachedSearch, a novel training-free method to accelerate test-time search for video diffusion models. This technique significantly reduces the computational cost of generating high-quality vid…
-
New framework enhances physical consistency in video diffusion models
Researchers have developed a new fine-tuning framework called VPT to enhance the physical consistency of video diffusion models. This framework addresses limitations in existing methods by introducing a role-aware signa…
-
DreamForge-World 0.1 Preview enables real-time interactive simulations on consumer GPUs
Researchers have introduced DreamForge-World 0.1 Preview, a foundational world model designed for real-time interactive simulations. This model adapts existing video generation architectures, such as LongLive 1 and Wan2…
-
New frameworks and benchmarks accelerate interactive video world models
Researchers have developed new methods to accelerate interactive video world models, which generate video content based on user camera movements. "Light Interaction" offers a training-free approach by adaptively managin…