Mindket

Lotis Demo

Newversion 1 · updated

Overview

Runs a Gradio demo of Lotis from fnnBsch, built on DINOv2 and DINOv3 models and a trained checkpoint. For people who want to try the model in a browser or read how it is wired.

Lotis Demo is a kit in the Research 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, with the version listed in the repository's .python-version file
  • The huggingface_hub package, which the first command installs
  • The packages listed in requirements.txt
Runs in
  • A web browser: open the Space page on Hugging Face and use it there.
  • Windows, macOS or Linux: run a copy on your own computer with Python.
Start with
pip install -U huggingface_hub
hf download fnnBsch/lotis-demo --repo-type space --local-dir lotis-demo
cd lotis-demo

Platform

WindowsOperating system
macOSOperating system
LinuxOperating system

About

What it is

Lotis Demo is a Gradio demo from the fnnBsch account. It lists three models, two from facebook and one from fnnBsch's own weights repository. The repository also carries a trained file, final_model.pth, with its settings in final_config.yaml. The card gives no written description, so the page is the way to see what it does.

Who it suits

Researchers and students who want to try the Lotis model online, and developers who want to read how it sits on top of the DINO models it names.

IndustryWho uses itHow they use itExample
ResearchMachine learning researchersTry the Lotis model on the sample inputsOpen the Space and pick one of the examples
EducationStudentsSee a model built on a pretrained backboneRun the demo, then read app.py
SoftwareDevelopersStudy how the lotis package is wired to the appLook through the lotis folder in a local copy

If you need a documented tool, you can skip it, because the card does not describe the model.

Where to use it

The demo runs in these places:

  • A web browser: open the Space page on Hugging Face and use it there.
  • Windows, macOS or Linux: run a copy on your own computer with Python.
Use caseWhoWhat they get back
Try the model onlineCurious visitorsWhatever the Gradio page returns for the input they give it
Study the codeDevelopersAn app file, a lotis package, an examples folder and the trained checkpoint
Run it locallyResearchersThe same Gradio demo on their own computer

How to set it up

You need a few things first:

  • Python, with the version listed in the repository's .python-version file
  • The huggingface_hub package, which the first command installs
  • The packages listed in requirements.txt

The steps download the Space, install Gradio at the version the Space uses, add the other packages and start the app.

  1. Install the Hugging Face package.
  2. Download the Space into a folder called lotis-demo.
  3. Move into that folder.
  4. Install Gradio 6.5.1.
  5. Install the packages from requirements.txt.
  6. Start the app.
pip install -U huggingface_hub
hf download fnnBsch/lotis-demo --repo-type space --local-dir lotis-demo
cd lotis-demo
pip install gradio==6.5.1
pip install -r requirements.txt
python app.py

How to use it

Open the Space page on Hugging Face, or start the local copy with the last command above. Gradio serves a web page, and the examples folder suggests sample inputs you can try first.

python app.py
ToolWhat it does
hf downloadCopies the Space's files into a folder on your computer
python app.pyStarts the demo on your own computer

Example

You open the Space page, choose one of the sample inputs and see what the model returns. The card does not list the exact inputs or outputs, so the page is the guide.

For newcomers and experts

If you are new to this, open the Space page and try a sample input first. You do not need to install anything for that. A local copy is only worth the setup when you want to read the code.

If you know the field, the demo pairs a trained checkpoint with DINO models from facebook and from fnnBsch's own weights repository. The code lives in a lotis folder next to app.py, and the hosted Space runs on the zero-a10g hardware tier.

  1. You open the Space or run python app.py
  2. A Gradio page takes your input
  3. The Lotis checkpoint and DINO models run
  4. The result shows on the page

Good to know

The card gives no list of inputs, outputs or limits.

  • License: mit, as the Space lists it.
  • Cost to run: none named. The hosted Space runs on the zero-a10g hardware at Hugging Face.
  • Data it reaches: what you give the demo, plus the model files it names, which a local copy downloads from Hugging Face.
  • Not for: none stated in the card.

README and files

README

Lotis Demo

Runs a Gradio demo of Lotis from fnnBsch, built on DINOv2 and DINOv3 models and a trained checkpoint. For people who want to try the model in a browser or read how it is wired.

Made by fnnBsch 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: Lotis Demo is a Gradio demo from the fnnBsch account. It lists three models, two from facebook and one from fnnBsch's own weights repository. The repository also carries a trained file, final_model.pth, with its settings in final_config.yaml. The card gives no written description, so the page is the way to see what it does.

Who it suits: Researchers and students who want to try the Lotis model online, and developers who want to read how it sits on top of the DINO models it names.

Industry | Who uses it | How they use it | Example
Research | Machine learning researchers | Try the Lotis model on the sample inputs | Open the Space and pick one of the examples
Education | Students | See a model built on a pretrained backbone | Run the demo, then read app.py
Software | Developers | Study how the lotis package is wired to the app | Look through the lotis folder in a local copy

If you need a documented tool, you can skip it, because the card does not describe the model.

Where to use it: The demo runs in these places:

  • A web browser: open the Space page on Hugging Face and use it there.
  • Windows, macOS or Linux: run a copy on your own computer with Python.
Use case | Who | What they get back
Try the model online | Curious visitors | Whatever the Gradio page returns for the input they give it
Study the code | Developers | An app file, a lotis package, an examples folder and the trained checkpoint
Run it locally | Researchers | The same Gradio demo on their own computer

How to set it up: You need a few things first:

  • Python, with the version listed in the repository's .python-version file
  • The huggingface_hub package, which the first command installs
  • The packages listed in requirements.txt

The steps download the Space, install Gradio at the version the Space uses, add the other packages and start the app.

  1. Install the Hugging Face package.
  2. Download the Space into a folder called lotis-demo.
  3. Move into that folder.
  4. Install Gradio 6.5.1.
  5. Install the packages from requirements.txt.
  6. Start the app.
pip install -U huggingface_hub
hf download fnnBsch/lotis-demo --repo-type space --local-dir lotis-demo
cd lotis-demo
pip install gradio==6.5.1
pip install -r requirements.txt
python app.py

How to use it: Open the Space page on Hugging Face, or start the local copy with the last command above. Gradio serves a web page, and the examples folder suggests sample inputs you can try first.

python app.py
Tool | What it does
hf download | Copies the Space's files into a folder on your computer
python app.py | Starts the demo on your own computer

Example: You open the Space page, choose one of the sample inputs and see what the model returns. The card does not list the exact inputs or outputs, so the page is the guide.

For newcomers and experts: If you are new to this, open the Space page and try a sample input first. You do not need to install anything for that. A local copy is only worth the setup when you want to read the code.

If you know the field, the demo pairs a trained checkpoint with DINO models from facebook and from fnnBsch's own weights repository. The code lives in a lotis folder next to app.py, and the hosted Space runs on the zero-a10g hardware tier.

You open the Space or run python app.py
A Gradio page takes your input
The Lotis checkpoint and DINO models run
The result shows on the page

Good to know: The card gives no list of inputs, outputs or limits.

  • License: mit, as the Space lists it.
  • Cost to run: none named. The hosted Space runs on the zero-a10g hardware at Hugging Face.
  • Data it reaches: what you give the demo, plus the model files it names, which a local copy downloads from Hugging Face.
  • Not for: none stated in the card.

On Hugging Face, 13 November 2026

  • Likes: 2
  • Built with: gradio
  • License: mit

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
Lotis Demo This page2gradiomit
Open VLM LeaderboardShares gradio1,034gradioapache-2.0
Face SwapShares gradio808gradiocc-by-nc-sa-4.0
TTS Spaces ArenaShares gradio493gradiozlib
Depth Anything 3Shares gradio490gradiocc-by-nc-4.0
BLIPShares gradio431gradiobsd-3-clause
Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13.

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 Research

See all in Research

EarthJev

dBenf · Kit

Answers typed questions about satellite image patches from all 12 Sentinel-2 bands, returning a probability for each option without writing text. A Qwen3.5-0.8…

New

getting-over-it-rl-jax

zimmerk4 · Kit

Plays the full game Getting Over It from the bottom to the end with a small trained policy network that learned inside a JAX physics simulator. For reinforceme…

New

ReFoCo

yuji-nozawa · Kit

Pretrained vision transformer checkpoints in three sizes from a research paper on training attention heads to focus on image regions. For researchers who extra…

New