prismstream-demo
prismstream-demo
Text-to-image with region conditioning. Paint a mask, describe what belongs inside it, watch it argue with you.
This card is generated from the entry's metadata in src/data/hub.js. Write a
card field on the entry to replace it with a real one.
How to use it
# Clone and run it locally
git clone https://huggingface.co/spaces/bluzen/prismstream-demo
cd prismstream-demo && pip install -r requirements.txt && python app.py
Details
| Task | Text-to-Image |
| Runtime | A10G |
| SDK | Gradio |
| Licence | Apache-2.0 |
Limitations
Every space the lab publishes carries the biases of the corpus it came from, and ours is illustration-heavy. Measure before you trust it.