AI Paper Atlas

Research map / Video / Video generation

StreamDiT: Real-Time Streaming Text-to-Video Generation

Akio Kodaira, Tingbo Hou, Ji Hou, Markos Georgopoulos, Felix Juefei-Xu, Masayoshi Tomizuka, Yue Zhao

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 42 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train StreamDiT with all chunk sizes [1,2,4,8,16] mixed instead of chunk size 1 only (ablation)StreamDiT-4B · VBench mixed-training ablationQuality Score: 0.8129 -> 0.8144Improved
mix chunk sizes [1,2] with chunk size 1 (ablation)StreamDiT-4B · VBench mixed-training ablationQuality Score: 0.8129 -> 0.8100Hurt
mix chunk sizes [1,2,4] (ablation)StreamDiT-4B · VBench mixed-training ablationQuality Score: 0.8129 -> 0.8080Hurt
mix chunk sizes [1,2,4,8] (ablation)StreamDiT-4B · VBench mixed-training ablationQuality Score: 0.8129 -> 0.8076Hurt
StreamDiT training instead of FIFO-Diffusion inference-only streamingStreamDiT-4B · VBenchQuality Score: 0.7981 -> 0.8185Improved
StreamDiT training instead of ReuseDiffuseStreamDiT-4B · VBenchQuality Score: 0.8019 -> 0.8185Improved
StreamDiT instead of FIFO-DiffusionStreamDiT-4B · VBenchDynamic Degree: 0.3094 -> 0.5240Improved
StreamDiT instead of FIFO-DiffusionStreamDiT-4B · VBenchTemporal Flickering: 0.9796 -> 0.9671Hurt
StreamDiT instead of FIFO-DiffusionStreamDiT-4B · VBenchMotion Smoothness: 0.9889 -> 0.9861Hurt
StreamDiT instead of FIFO-DiffusionStreamDiT-4B · VBenchSubject Consistency: 0.9412 -> 0.9622Improved
multistep distillation to 8 steps without CFGStreamDiT-4B · VBenchQuality Score: 0.8185 -> 0.8163No clear effect
multistep distillation to 8 steps without CFGStreamDiT-4B · VBenchDynamic Degree: 0.5240 -> 0.7040Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy