RepoAlerts
SponsorGet alerts

zylwithxy/HRDiT

Get alerts like thisView on GitHubWebsiteShare on X

Can I trust it?

Worth a closer look before you use it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active Check

    Last change 50 days ago.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

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

What it is

Research code for HRDiT, a training-free method that adapts off-the-shelf FLUX.1-dev diffusion transformers to generate high-resolution images up to 4K. It combines Spatial Position Alignment (SPA) to fix spatial disorder and Head-adaptive Attention Pruning (HAP) to shorten…

Who it's for

Researchers and developers running FLUX.1-dev diffusion transformers who need high-resolution text-to-image generation without training

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 zylwithxy/HRDiT in my project. Follow its README: https://github.com/zylwithxy/HRDiT. Explain each step and check it is safe before running anything.

Star curve

298From 79 to 298 stars between 18 Sept 2026 and 22 Oct 2026.

Alternatives

Similar projects named in its profile. Each link searches the directory.

Get alerts for repos like this

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

18,919 GitHub repos watched and ranked every hour. Figures as of 22 October 2026.

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.

[![zylwithxy/HRDiT on RepoAlerts](https://repoalerts.com/badge/zylwithxy/HRDiT.svg)](https://repoalerts.com/repo/zylwithxy/HRDiT?ref=badge)
Share on X
  • zjwfufu/SMD

    A research codebase implementing SMD, an on-policy distillation method that trains few-step diffusion students from teacher models. It provides training configurations and inference scripts for image,

    LibraryModels & inferencePython · 237 stars · +205 this week · 15 days old

  • OpenMOSS/MOSS-Image

    Official code for MOSS-Image, a 5B-parameter diffusion transformer for text-to-image generation. It focuses on rendering legible text inside images, layout control of text and visual elements, long pr

    ModelModels & inferencePython · 1,325 stars · +1,325 this week · 6 days old

  • Tencent-Hunyuan/Prism

    Research code for Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K resolution. It partitions tokens into spatiotemporal zones and adapts bloc

    Models & inferencePython · 649 stars · +250 this week · 31 days old

  • chenglou/handwired

    A research project that compiles ordinary JavaScript/TypeScript control flow (if-else, loops, state) into a matrix multiplication network using only addition, multiplication and ReLU over floats. The

    Models & inferenceTypeScript · 1,875 stars · +1,763 this week · 7 days old

  • KohakuBlueleaf/KohakuMossTrainer

    A finetuning framework for the MOSS-Image text-to-image model. It trains LyCORIS adapters (LoRA, LoHa, LoKr, DoRA and others) or full finetunes on native-resolution text-image data, with memory profil

    Models & inferencePython · 103 stars · +103 this week · 4 days old

  • zita-ch/supermimic_vibed

    Unofficial reimplementation of the SuperMimic humanoid whole-body control method, built from the paper since no official code exists. Trains a single Unitree G1 motion-tracking policy on 40 LAFAN1 mot

    AI agentsPython · 92 stars · +92 this week · 1 day old