# Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/enhancing-train-free-infinite-frame-generation-for-consistent-long-videos
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/enhancing-train-free-infinite-frame-generation-for-consistent-long-videos.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-05-22T04:01:52+00:00
Episode link: https://share.transistor.fm/s/a48cc988
Audio file: https://media.transistor.fm/a48cc988/e75cf03f.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/enhancing-train-free-infinite-frame-generation-for-consistent-long-videos
Duration seconds: 1501

## Resource

🤗 Upvotes: 83 | cs.CV Authors: X. Feng, J. Zhu, M. Wu, C. Chen, F. Mao, H. Guo, J. Wu, X. Chu, K. Huang Title: Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos Arxiv: http://arxiv.org/abs/2605.18233v1 Abstract: Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the advantage of generating infinitely long videos with constant memory consumption. However, the mismatch between training and inference, coupled with the challenge of maintaining long-term consistency, limits the effective utilization of foundation models. To mitigate these concerns, we propose \textbf{MIGA}, a novel infinite-frame long video generation method. Firstly, we propose an effective two-stage alignment mechanism that mitigates the training-inference gap by reducing the excessive noise span fed to the model. We then introduce an innovative dual consistency enhancement mechanism, where the self-reflection approach corrects early high-noise frames and the long-range frame guidance approach leverages later low-noise frames with broad coverage to steer generation, jointly improving temporal consistency. Extensive experiments on VBench and NarrLV demonstrate the state-of-the-art performance of MIGA. Our project page is available at https://xiaokunfeng.github.io/miga_homepage/.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/enhancing-train-free-infinite-frame-generation-for-consistent-long-videos/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/daily-paper-cast-7079649/enhancing-train-free-infinite-frame-generation-for-consistent-long-videos.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.