StreamingEffect enables real-time 720p human-centric video effect generation on one GPU via teacher-student distillation, keyframe control, and a new 130K video dataset.
hub Mixed citations
Diffusion adversarial post-training for one-step video generation
Mixed citation behavior. Most common role is background (57%).
15
Pith papers citing it
Background
57% of classified citations
hub tools
citation-role summary
background 4
method 3
citation-polarity summary
representative citing papers
CausalCine enables real-time causal autoregressive multi-shot video generation via multi-shot training, content-aware memory routing for coherence, and distillation to few-step inference.
A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.
RTR-DiT distills a bidirectional DiT teacher into an autoregressive few-step model using Self Forcing and Distribution Matching Distillation, plus a reference-preserving KV cache, to enable stable real-time text- and reference-guided video stylization.
INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching distillation.
Salt improves low-step video generation quality by adding endpoint-consistent regularization to distribution matching distillation and using cache-conditioned feature alignment for autoregressive models.
The work introduces rCM, a score-regularized continuous-time consistency model that matches DMD2 quality on large models up to 14B parameters while improving diversity and enabling 1-4 step sampling.
Rolling Forcing generates multi-minute videos in real time by jointly denoising frames at increasing noise levels, anchoring attention to early frames, and using windowed distillation to limit error accumulation.
Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion for efficiency.
Lens is a 3.8B-parameter text-to-image model that reaches competitive or superior performance to >6B-parameter systems using 19.3% of the training compute of Z-Image through a densely captioned 800M dataset, multi-resolution batching, semantic VAE, strong language encoder, RL fine-tuning, and 4-step
TurboTalk uses progressive distillation from 4 steps to 1 step with distribution matching and adversarial training to achieve 120x faster single-step audio-driven talking avatar video generation.
OASIS reduces redundancy in diffusion models for real-world video super-resolution via attention specialization routing and progressive training, delivering state-of-the-art quality with 6.2x faster inference than prior one-step baselines.
Seedance 1.0 generates 5-second 1080p videos in about 41 seconds with claimed superior motion quality, prompt adherence, and multi-shot consistency compared to prior models.
Seedream 4.0 unifies text-to-image synthesis, image editing, and multi-image composition in an efficient diffusion transformer pretrained on billions of pairs and accelerated to 1.8 seconds for 2K output.
citing papers explorer
-
CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives
CausalCine enables real-time causal autoregressive multi-shot video generation via multi-shot training, content-aware memory routing for coherence, and distillation to few-step inference.
-
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Seedance 1.0 generates 5-second 1080p videos in about 41 seconds with claimed superior motion quality, prompt adherence, and multi-shot consistency compared to prior models.
-
Seedream 4.0: Toward Next-generation Multimodal Image Generation
Seedream 4.0 unifies text-to-image synthesis, image editing, and multi-image composition in an efficient diffusion transformer pretrained on billions of pairs and accelerated to 1.8 seconds for 2K output.