RepoAlerts

Linum-AI/pjit-21k

Model

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 13 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 12 days ago.

  • Licence OK

    Apache-2.0: 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

A 2B-parameter pixel-space text-to-image model (P-JiT 21K) trained for about $21K of compute. It generates images from dense captions at roughly 1 MP sizes and is released as an experimental research checkpoint. It cannot render text, posters or logos.

Who it's for

Researchers and developers exploring efficient text-to-image training and running CUDA GPUs for image generation

How to use it

Install

pip install -e .

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 Linum-AI/pjit-21k in my project. Follow its README: https://github.com/Linum-AI/pjit-21k. Explain each step and check it is safe before running anything.

Star curve

79From 0 to 79 stars between 3 Nov 2026 and 16 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.

[![Linum-AI/pjit-21k on RepoAlerts](https://repoalerts.com/badge/Linum-AI/pjit-21k.svg)](https://repoalerts.com/repo/Linum-AI/pjit-21k?ref=badge)
Share on X

  • awv199cxiitrxw/wan2-7-image-prompts-ja

    A set of eight tested text-to-image prompt recipes for the Wan 2.7 Image model (wan2.7-image), each with an example render, aspect ratio and per-image cost. Recipes follow a subject, light, framing, s

    AI skillCreative toolsPython · 63 stars · +61 this week · 30 days old

  • MiniMax-AI/MiniMax-H3-Image

    Open-source model for text-to-image generation and image editing, part of the MiniMax H3 family. Generates about 16 megapixel images at multiple aspect ratios and edits up to 16 reference images. Dist

    ModelModels & inferencePython · 402 stars · +402 this week · 7 days old

  • rockmatrix-ai/EdgeRock

    A 4B-parameter multimodal model for text and image reasoning, with constant-size attention history (about 72 MiB per sequence at 256K context) to free GPU memory for sustained reasoning and concurrent

    Models & inferencePython · 1,143 stars · +148 this week · 40 days old

  • apimartfe05r4/wan2.7-image-prompts-ja

    Collection of tested image prompt recipes for the Wan 2.7 Image model, with example renders, aspect ratios and the model id wan2.7-image. It documents calling the model through the APIMart OpenAI-comp

    ResourceModels & inferencePython · 59 stars · 36 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 · 2,913 stars · +148 this week · 32 days old

  • alexturkey/z-image-turbo-pascal-4gb

    Unofficial Windows setup for text-to-image with Z-Image-Turbo (Q8_0 GGUF) on a 4 GB NVIDIA GTX 1050 Ti, using stable-diffusion.cpp with a cuDNN VAE. Includes engine patches, a build recipe, pinned dow

    ResourceModels & inferencePython · 135 stars · +135 this week · 2 days old