Pith. sign in

REVIEW 5 cited by

NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.12346 v1 pith:4U5CC2PN submitted 2023-03-22 cs.CV cs.AI

Shengming Yin , Chenfei Wu , Huan Yang , Jianfeng Wang , Xiaodong Wang , Minheng Ni , Zhengyuan Yang , Linjie Li
show 8 more authors
Shuguang Liu Fan Yang Jianlong Fu Gong Ming Lijuan Wang Zicheng Liu Houqiang Li Nan Duan
This is my paper · ORCID
classification cs.CVcs.AI
keywords longdiffusionvideosgenerationvideoframesmodelextremely
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we propose NUWA-XL, a novel Diffusion over Diffusion architecture for eXtremely Long video generation. Most current work generates long videos segment by segment sequentially, which normally leads to the gap between training on short videos and inferring long videos, and the sequential generation is inefficient. Instead, our approach adopts a ``coarse-to-fine'' process, in which the video can be generated in parallel at the same granularity. A global diffusion model is applied to generate the keyframes across the entire time range, and then local diffusion models recursively fill in the content between nearby frames. This simple yet effective strategy allows us to directly train on long videos (3376 frames) to reduce the training-inference gap, and makes it possible to generate all segments in parallel. To evaluate our model, we build FlintstonesHD dataset, a new benchmark for long video generation. Experiments show that our model not only generates high-quality long videos with both global and local coherence, but also decreases the average inference time from 7.55min to 26s (by 94.26\%) at the same hardware setting when generating 1024 frames. The homepage link is \url{https://msra-nuwa.azurewebsites.net/}

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MotionShot: Adaptive Motion Transfer across Arbitrary Objects for Text-to-Video Generation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MotionShot transfers motion from a reference video to an unseen target object in text-to-video generation by combining semantic and morphological alignment in a training-free pipeline.

  2. TokensGen: Harnessing Condensed Tokens for Long Video Generation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    TokensGen generates consistent long videos by representing each clip as condensed semantic tokens, generating all tokens jointly from text, and stitching clips with adaptive FIFO denoising.

  3. LumosFlow: Motion-Guided Long Video Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    LumosFlow generates long videos by combining large-motion key frame generation, latent optical flow diffusion, and a ControlNet-style refinement module.

  4. ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos

    cs.CV 2025-05 conditional novelty 6.0 of 10

    ProphetDWM is a one-stage diffusion world model that jointly predicts future driving video and low-level actions from a current frame and a short action sequence.

  5. LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model

    cs.CV 2025-06 reject novelty 5.0 of 10

    A hierarchical coarse-to-fine diffusion transformer with cross-granularity distillation improves long-term driving video prediction, but the reported gains may be inflated by future-derived text prompts and a selected...

Pith tools