Text-to-Image
Transformers
English
SupraDiT
feature-extraction
small
supra
image
flux
img
t2i
from scratch
custom_code
Instructions to use SupraLabs/Supra2-IMG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SupraLabs/Supra2-IMG with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SupraLabs/Supra2-IMG", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Local in-browser demo (WebGPU)
#6
by sm079 - opened
Thanks for releasing this! Because the model is so small, it can run reasonably fast entirely on your browser:
https://sm079.github.io/supra2-img-web/
Everything stays local, prompts and images never leave your computer, and there's no server or install. The model downloads once (about 1 GB) and is cached in the browser, so later visits load from your device.
Sampling matches inference.py (Euler, CFG, 50 steps). Source: https://github.com/sm079/supra2-img-web. Converted weights, with attribution: https://huggingface.co/sm079/supra2-img-web
Wow! This is sooo cool! Thanks so much 🤗 ❤️


