TRELLIS.2-Text-to-3D (Rerun)

TRELLIS.2-Text-to-3D (Rerun)

Turn a text prompt or a picture into a 3D model with Microsoft's TRELLIS.2 in a Gradio app. Runs in your browser or on your own computer with Python 3.12.

Made by prithivMLmods 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: This Space is a Gradio app that makes 3D models. You can start from a text prompt, which the app first turns into an image, or start from an image you already have.

The 3D step uses TRELLIS.2 at 4B size. The app also names FLUX.1-dev, Z-Image-Turbo, DINOv3 and CLIP models for the other parts of the work.

Who it suits: It suits people who want to see a text or image become a 3D object without installing anything, and developers who want to read how several models chain into one pipeline.

Industry | Who uses it | How they use it | Example
Game development | Indie developers | Turn a concept prompt or sketch image into a 3D asset | Trying out a prop idea before modelling it by hand
3D design | Artists | Start from a picture and look at the generated model | Comparing a few source images for the same object
AI development | Developers | Read app.py and the trellis2 folder | Learning how the 3D step is wired to the image step
Education | Students | Open the page and try the example images | Seeing what image-to-3D can do

Skip it if you need production-ready 3D files with support, since this is a demo page.

Where to use it: The app runs in these places.

• A web browser, on the Space's page at Hugging Face
• A local copy on Windows, macOS or Linux, running Python 3.12
• Hugging Face's zero-a10g hardware, where the online Space runs

Use case | Who | What they get back
Text to 3D | Anyone curious | A 3D model made from a prompt
Image to 3D | Artists | A 3D model made from a picture
Study the pipeline | Developers | A repository with the app and the trellis2 code

How to set it up: Online you only need a browser. A local copy needs these.

• Python 3.12 on Windows, macOS or Linux
• The pip command
• Room on disk for the several models the app names

1. Install the huggingface_hub package.
2. Download the Space's files into a folder with the hf command.
3. Move into that folder.
4. Install gradio at version 6.14.0.
5. Install the packages listed in requirements.txt.
6. Start the app with python app.py.

pip install -U huggingface_hub
hf download prithivMLmods/TRELLIS.2-Text-to-3D --repo-type space --local-dir TRELLIS.2-Text-to-3D
cd TRELLIS.2-Text-to-3D
pip install gradio==6.14.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page, or run the command below in your copy and open the page the app serves. Then type a prompt or add an image and run it.

python app.py

Example: You open the Space, type a short description of an object and run it. The app makes a picture first, then builds a 3D model from it and shows the result on the page.

For newcomers and experts: If you are new, open the Space's page and try one of the example images first, because an image is the shortest route to a 3D result. Then try a text prompt.

If you know the field, this is a multi-model pipeline: a text-to-image stage feeds TRELLIS.2 4B, with DINOv3 and CLIP encoders named beside it. The repository holds 266 files, mostly the trellis2 code, and an autotune_cache.json file. Online it runs on zero-a10g hardware with Gradio 6.14.0.

Type a prompt or add an image
A prompt becomes an image first
TRELLIS.2 builds a 3D model from it
The model shows on the same page

Good to know: The name carries the word Rerun, and the source does not explain it. Hugging Face lists the Space with Gradio and MCP tags.

• License: apache-2
• Cost to run: none named
• Data it reaches: only the model repositories it names. The source says nothing else.

On Hugging Face, 13 November 2026

• Likes: 58
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/prithivMLmods/TRELLIS.2-Text-to-3D
• Files: https://huggingface.co/spaces/prithivMLmods/TRELLIS.2-Text-to-3D/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.