Sketch2lineart

Sketch2lineart

Turns a rough sketch into clean line art with an SDXL-based model and a custom line art LoRA, in a Gradio demo. It suits illustrators, comic makers and anime artists.

Made by tori29umai 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: Sketch2lineart is a Gradio demo that turns a rough sketch into line art. The Space names the animagine-xl-3.1 image model, a lineart model from tori29umai, a LoRA collection, an SDXL VAE fix and the wd-vit-tagger-v3 image tagger. It runs on ZeroGPU at Hugging Face.

Who it suits: Illustrators, comic makers and anime artists who want a clean outline from a rough drawing. It also suits hobbyists who want to try AI-assisted inking.

Title: Who cleans up sketches with AI
Industry | Who uses it | How they use it | Example
Illustration | Illustrators | Turn a rough sketch into a clean outline | Ink a character sketch
Comics | Comic and manga makers | Prepare line art for colouring | Clean up a page layout drawing
Animation | Animation artists | Get quick line art from a key pose | Outline a pose sketch
Hobby | Drawing fans | Try AI-assisted inking | Upload a doodle and compare the result

If you need to colour or render a finished picture, you can skip it, since the source describes line art only.

Where to use it:

• A web browser: the Space runs on Hugging Face with nothing to install
• Windows, macOS or Linux with Python, from a local copy

Use case | Who | What they get back
Clean up a rough sketch | Illustrators | A line art version of the sketch
Prepare line art for colouring | Comic makers | An outline you can colour in your own tools
Try AI-assisted inking | Hobbyists | A quick result from one upload

How to set it up: Using the Space online needs nothing. A local copy needs Python and the packages the repository lists. The Space runs on ZeroGPU at Hugging Face, so a local copy may need a capable GPU.

• Python with pip
• The Python packages in requirements.txt

1. Install the Hugging Face hub package and download the Space into a folder.
2. Move into that folder.
3. Install Gradio 4.29.0, then the packages from requirements.txt.
4. Start the app with Python.

pip install -U huggingface_hub
hf download tori29umai/sketch2lineart --repo-type space --local-dir sketch2lineart
cd sketch2lineart
pip install gradio==4.29.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space in your browser, or start the local copy with the command below and open the page Gradio serves. Upload a sketch and read the line art it returns. The source lists no further steps.

python app.py

Example: You upload a pencil sketch of a character. The app returns a cleaner line drawing of the same figure that you can save and colour elsewhere.

For newcomers and experts: If you are new to this, open the Space and upload a simple sketch with clear strokes. Compare the result with your original.

If you know the field, the Space combines an SDXL anime base model, animagine-xl-3.1, with a lineart model and a LoRA set, and it names a VAE fix for half precision. A tagger model, wd-vit-tagger-v3, is also listed. The config file and a utils folder hold the rest. Beyond those names, the source does not describe how they combine.

You upload a rough sketch
The models process the image
A clean line drawing is produced
You save the result

Good to know:

• Hardware: the Space runs on zero-a10g at Hugging Face
• Focus: line art from sketches, not coloured pictures
• License: mit
• Cost to run: none named

On Hugging Face, 13 November 2026

• Likes: 315
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/tori29umai/sketch2lineart
• Files: https://huggingface.co/spaces/tori29umai/sketch2lineart/tree/main

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.