TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper
•
2512.16093
•
Published
•
90
Read But Not Implemented
-
-
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 221 -
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 200 -
Sharp Monocular View Synthesis in Less Than a Second
Paper • 2512.10685 • Published • 24 -
Latent Implicit Visual Reasoning
Paper • 2512.21218 • Published • 63 -
SemanticGen: Video Generation in Semantic Space
Paper • 2512.20619 • Published • 88 -
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 167 -
Spatia: Video Generation with Updatable Spatial Memory
Paper • 2512.15716 • Published • 28 -
The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
Paper • 2512.19693 • Published • 61 -
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation
Paper • 2511.14993 • Published • 227 -
PersonaLive! Expressive Portrait Image Animation for Live Streaming
Paper • 2512.11253 • Published • 32 -
Diffusion Transformers with Representation Autoencoders
Paper • 2510.11690 • Published • 165 -
1.58-bit FLUX
Paper • 2412.18653 • Published • 86 -
InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion
Paper • 2512.17504 • Published • 94 -
ProEdit: Inversion-based Editing From Prompts Done Right
Paper • 2512.22118 • Published • 16 -
Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield
Paper • 2511.22677 • Published • 28 -
FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction
Paper • 2512.16900 • Published • 10 -
StoryMem: Multi-shot Long Video Storytelling with Memory
Paper • 2512.19539 • Published • 17 -
LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation
Paper • 2512.23576 • Published • 62 -
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 86 -
Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion
Paper • 2512.23709 • Published • 43 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 166