Mindket

Krea Sandbox

Newversion 1 · updated

Overview

A small Gradio sandbox for trying the AST-1320/Krea-2-Turbo-Diffusers model, which by its name is packaged for Diffusers. The README gives no description, so read app.py to see what it does.

Krea Sandbox is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.

At a glance

You need
  • Python 3.12 with pip
  • Gradio 6.31.0
  • The packages in requirements.txt
Runs in
  • A web browser: open the Space page on Hugging Face
  • Windows, macOS or Linux: run a copy with Python 3.12
  • Hugging Face Spaces: the Space is set to zero-a10g hardware there
Start with
pip install -U huggingface_hub
hf download AST-1320/Krea-sandbox --repo-type space --local-dir Krea-sandbox
cd Krea-sandbox

Platform

WindowsOperating system
macOSOperating system
LinuxOperating system

About

What it is

Krea Sandbox is a small Gradio app hosted as a Hugging Face Space. It names one model, AST-1320/Krea-2-Turbo-Diffusers, which by its name is packaged for the Diffusers library. The README holds only Hugging Face's default text, so this page rests on the file list, and app.py is the place to confirm what it does.

Who it suits

People who want to try that model through a browser, and developers who want a small Gradio wrapper to read, will get the most from it. The rows below are judgment from the name and the files, not claims from the author.

IndustryWho uses itHow they use itExample
DesignDesigners and artistsTry the model through the interface, if it makes images as its name hintsTyping a short prompt and looking at the result
SoftwareDevelopersRead app.py and requirements.txt to see how a Gradio app wraps a modelChecking how the model is loaded
EducationStudentsUse the small Space as an example of a hosted model demoDownloading the folder and running python app.py

You can skip it if you need documented features or a described model, since neither is in the source.

Where to use it

Use it in a browser tab, or run a copy on your own computer.

  • A web browser: open the Space page on Hugging Face
  • Windows, macOS or Linux: run a copy with Python 3.12
  • Hugging Face Spaces: the Space is set to zero-a10g hardware there
Use caseWhoWhat they get back
Try the model onlineAnyone with a browserWhatever the interface offers, which the README does not describe
Run a local copyDevelopers with Python 3.12The same app on their own machine
Read the codeLearnersapp.py and requirements.txt to study

How to set it up

Using the Space online needs nothing. A local copy needs Python 3.12 and the listed packages.

  • Python 3.12 with pip
  • Gradio 6.31.0
  • The packages in requirements.txt
  1. Install the Hugging Face hub package.
  2. Download the Space's files into a folder.
  3. Move into that folder.
  4. Install Gradio 6.31.0, then the listed packages.
  5. Run app.py with Python.
pip install -U huggingface_hub
hf download AST-1320/Krea-sandbox --repo-type space --local-dir Krea-sandbox
cd Krea-sandbox
pip install gradio==6.31.0
pip install -r requirements.txt
python app.py

How to use it

Open the Space page and use the interface you find there. With a local copy, run the app file and use the interface it starts. The source shows no other commands or tools.

python app.py

Example

Open the Space and give the interface a short text prompt, such as a description of a scene. If the model makes images as the name hints, a picture would come back. The README does not confirm the inputs or outputs.

For newcomers and experts

Open the Space and try one short prompt to see what the interface does. If nothing explains itself, read app.py, which sits next to requirements.txt at the top of the repository.

If you know the field, the model's name suggests a Diffusers release with a Turbo variant, but the record says nothing about its size, speed or output. The Space itself runs on zero-a10g hardware at Hugging Face, and the record gives no figure for a local run.

  1. You open the Space or run python app.py
  2. Gradio starts the interface from app.py
  3. You send a prompt
  4. The app works with the named model

Good to know

  • License: Apache-2.0
  • Cost to run: no API key, account or paid service named
  • Data it reaches: none named, beyond whatever you type into the app
  • Not for: anything that needs documented behavior, since the source gives no limits and no description

README and files

README

Krea Sandbox

A small Gradio sandbox for trying the AST-1320/Krea-2-Turbo-Diffusers model, which by its name is packaged for Diffusers. The README gives no description, so read app.py to see what it does.

Made by AST-1320 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Krea Sandbox is a small Gradio app hosted as a Hugging Face Space. It names one model, AST-1320/Krea-2-Turbo-Diffusers, which by its name is packaged for the Diffusers library. The README holds only Hugging Face's default text, so this page rests on the file list, and app.py is the place to confirm what it does.

Who it suits: People who want to try that model through a browser, and developers who want a small Gradio wrapper to read, will get the most from it. The rows below are judgment from the name and the files, not claims from the author.

Industry | Who uses it | How they use it | Example
Design | Designers and artists | Try the model through the interface, if it makes images as its name hints | Typing a short prompt and looking at the result
Software | Developers | Read app.py and requirements.txt to see how a Gradio app wraps a model | Checking how the model is loaded
Education | Students | Use the small Space as an example of a hosted model demo | Downloading the folder and running python app.py

You can skip it if you need documented features or a described model, since neither is in the source.

Where to use it: Use it in a browser tab, or run a copy on your own computer.

  • A web browser: open the Space page on Hugging Face
  • Windows, macOS or Linux: run a copy with Python 3.12
  • Hugging Face Spaces: the Space is set to zero-a10g hardware there
Use case | Who | What they get back
Try the model online | Anyone with a browser | Whatever the interface offers, which the README does not describe
Run a local copy | Developers with Python 3.12 | The same app on their own machine
Read the code | Learners | app.py and requirements.txt to study

How to set it up: Using the Space online needs nothing. A local copy needs Python 3.12 and the listed packages.

  • Python 3.12 with pip
  • Gradio 6.31.0
  • The packages in requirements.txt
  1. Install the Hugging Face hub package.
  2. Download the Space's files into a folder.
  3. Move into that folder.
  4. Install Gradio 6.31.0, then the listed packages.
  5. Run app.py with Python.
pip install -U huggingface_hub
hf download AST-1320/Krea-sandbox --repo-type space --local-dir Krea-sandbox
cd Krea-sandbox
pip install gradio==6.31.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space page and use the interface you find there. With a local copy, run the app file and use the interface it starts. The source shows no other commands or tools.

python app.py

Example: Open the Space and give the interface a short text prompt, such as a description of a scene. If the model makes images as the name hints, a picture would come back. The README does not confirm the inputs or outputs.

For newcomers and experts: Open the Space and try one short prompt to see what the interface does. If nothing explains itself, read app.py, which sits next to requirements.txt at the top of the repository.

If you know the field, the model's name suggests a Diffusers release with a Turbo variant, but the record says nothing about its size, speed or output. The Space itself runs on zero-a10g hardware at Hugging Face, and the record gives no figure for a local run.

You open the Space or run python app.py
Gradio starts the interface from app.py
You send a prompt
The app works with the named model

Good to know:

  • License: Apache-2.0
  • Cost to run: no API key, account or paid service named
  • Data it reaches: none named, beyond whatever you type into the app
  • Not for: anything that needs documented behavior, since the source gives no limits and no description

On Hugging Face, 13 November 2026

  • Likes: 1
  • Built with: gradio
  • License: apache-2.0

Links

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.

Files
README.md  4 KB

1 file, 4 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Compare with similar

Listed Hugging Face Spaces in the same category that share the most tags with this one.

ProductLikesBuilt withLicenseLast change
Krea Sandbox This page1gradioapache-2.0
MusicGenShares gradio5,116gradiocc-by-nc-4.0
Kokoro TTSShares gradio3,556gradioapache-2.0
Background RemovalShares gradio2,988gradiomit
Omni Image EditorShares gradio2,922gradiomit
Diffusers Image OutpaintShares gradio2,565gradioapache-2.0
Numbers as Mindket last read them, on 2026-11-12.

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

Huashu Design

alchaincyf · Skill

Turns a one-line request in your AI agent into a finished design: a launch animation, a clickable app prototype, an editable slide deck, an infographic or a se…

New29.4k

Guizang PPT Skill

op7418 · Skill

Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…

New29.8k

Claude Code Skills & Plugins

alirezarezvani · Skill

Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…

New29.8k

Similar in Productivity

See all in Productivity

Frontend Slides

zarazhangrui · Skill

Builds HTML presentations from scratch or from a PowerPoint file and shows visual style previews to pick from, for people who want web slides with no CSS or Ja…

New32.3k

IPTV

iptv-org · Kit

Collects publicly available live TV channels from many countries into playlists that any video player with live streaming can open. Made for viewers and for de…

New144k

upscaler

uwg · Kit

Holds a set of image upscaling models gathered from the OpenModelDB community, for people who want to enlarge low-resolution pictures with AI on their own comp…

New