Asymmetric CUDA-stream pipelining, a compile-friendly LLLite reformulation, and periodic conditioning refresh sustain 27-30 fps video stylization on a consumer GPU with a 2.13B MLLM text encoder and 0.39B distilled U-Net.
hub
Streamdit: Real-time streaming text-to-video generation
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
LongLive-RAG formulates long video generation as retrieval-augmented generation by treating self-generated latents as a dynamic searchable history and adding a Window Temporal Delta Loss for better retrieval.
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.
OphEdit enables text-guided editing of eye surgery videos without training by injecting preserved attention value tensors into the diffusion denoising process to maintain anatomical structure.
Sparse Forcing adds a native trainable sparsity mechanism and PBSA kernel to autoregressive diffusion video models, yielding higher VBench scores and 1.1-1.27x speedups on 5s to 1min generations.
Dreamer 4 is the first agent to obtain diamonds in Minecraft from only offline data by reinforcement learning inside a scalable world model that accurately predicts game mechanics.
Hybrid Forcing combines linear temporal attention for long-range retention, block-sparse attention for efficiency, and decoupled distillation to achieve real-time unbounded 832x480 streaming video generation at 29.5 FPS.
Live Avatar reports real-time streamable generation from a 14B audio-driven diffusion model at ~20 FPS on 5 H800s with stable identity over 10,000 seconds.
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
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.
LongLive is a causal autoregressive video generator that produces up to 240-second interactive videos at 20.7 FPS on one H100 GPU after 32 GPU-days of fine-tuning from a 1.3B short-clip model.
Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.
citing papers explorer
-
Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU
Asymmetric CUDA-stream pipelining, a compile-friendly LLLite reformulation, and periodic conditioning refresh sustain 27-30 fps video stylization on a consumer GPU with a 2.13B MLLM text encoder and 0.39B distilled U-Net.
-
LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation
LongLive-RAG formulates long video generation as retrieval-augmented generation by treating self-generated latents as a dynamic searchable history and adding a Window Temporal Delta Loss for better retrieval.
-
StreamingEffect: Real-Time Human-Centric Video Effect Generation
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.
-
OphEdit: Training-Free Text-Guided Editing of Ophthalmic Surgical Videos
OphEdit enables text-guided editing of eye surgery videos without training by injecting preserved attention value tensors into the diffusion denoising process to maintain anatomical structure.
-
Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
Sparse Forcing adds a native trainable sparsity mechanism and PBSA kernel to autoregressive diffusion video models, yielding higher VBench scores and 1.1-1.27x speedups on 5s to 1min generations.
-
Training Agents Inside of Scalable World Models
Dreamer 4 is the first agent to obtain diamonds in Minecraft from only offline data by reinforcement learning inside a scalable world model that accurately predicts game mechanics.
-
Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation
Hybrid Forcing combines linear temporal attention for long-range retention, block-sparse attention for efficiency, and decoupled distillation to achieve real-time unbounded 832x480 streaming video generation at 29.5 FPS.
-
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Live Avatar reports real-time streamable generation from a 14B audio-driven diffusion model at ~20 FPS on 5 H800s with stable identity over 10,000 seconds.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
-
Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
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.
-
LongLive: Real-time Interactive Long Video Generation
LongLive is a causal autoregressive video generator that produces up to 240-second interactive videos at 20.7 FPS on one H100 GPU after 32 GPU-days of fine-tuning from a 1.3B short-clip model.
-
Reward-Forcing: Autoregressive Video Generation with Reward Feedback
Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.
- FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion