RepoAlerts

Tencent-Hunyuan/MovieRoll

Model

Can I trust it?

Be careful with this one.

  • Warnings Check

    Very new: it was created 12 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 5 days ago.

  • Licence Careful

    No licence: legally you can't reuse the code, unless the README says otherwise.

Quick checks from public data. They help, but they are no guarantee.

What it is

A research framework for generating long-form videos, from a supervised Base model to a few-step Distilled model, with long-rollout generation designed to reduce degradation over time. Released with text-to-video and image-to-video checkpoints and inference code requiring…

Who it's for

Researchers and ML engineers running long video generation models on high-memory Hopper-class GPUs

How to use it

Install

pip install -r requirements.txt

From its README. Check it there before running it.

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up Tencent-Hunyuan/MovieRoll in my project. Follow its README: https://github.com/Tencent-Hunyuan/MovieRoll. Explain each step and check it is safe before running anything.

Star curve

266From 0 to 266 stars between 11 Nov 2026 and 22 Nov 2026.

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![Tencent-Hunyuan/MovieRoll on RepoAlerts](https://repoalerts.com/badge/Tencent-Hunyuan/MovieRoll.svg)](https://repoalerts.com/repo/Tencent-Hunyuan/MovieRoll?ref=badge)
Share on X

  • Tencent-Hunyuan/Hy-Nomas

    Open-source Python code for Hy-Nomas, an autoregressive video world generation model that produces interactive worlds from free-form text prompts or camera trajectories. The repository provides traini

    ModelModels & inferencePython · 603 stars · +21 this week · 33 days old

  • Tencent-Hunyuan/Prism

    A research framework for natively training joint video-audio generation models at up to 2K resolution, using dynamic sparse attention. It organizes tokens into spatiotemporal zones and assigns each a

    ModelModels & inferencePython · 1,518 stars · +1 this week · 62 days old

  • TencentARC/Looking-Ahead

    Research code and model weights for Future Chunk Prediction, a training method for autoregressive video generation. Auxiliary branches predict temporally distant video chunks from intermediate feature

    ModelModels & inferencePython · 275 stars · 32 days old

  • alexturkey/VideoTurko

    Memory patches and run recipes for stable-diffusion.cpp that aim to run the MiniMax H3 text-to-video model on a 4 GB GTX 1050 Ti, generating up to 209 frames in one pass, with image-to-video limited t

    ResourceModels & inferencePython · 112 stars · +112 this week · 3 days old

  • YinBo0927/FrameMorrow

    A research codebase for selecting historical video frames to condition long-horizon video generation. Prospective tokens predict useful history from observed frames and the current condition, and futu

    Creative toolsPython · 232 stars · 55 days old

  • apple-aiml-research/ml-fastframes

    Official implementation of FastFrames, two autoregressive two-step video diffusion models (1.3B and 14B) that generate 480p video at interactive latency, plus an optimized, camera-controllable version

    ModelModels & inferencePython · 134 stars · +134 this week · 5 days old