TextualDiffuser is a text-to-image generation tool powered by Stable Diffusion. It transforms natural language prompts into high-quality visuals, making AI-powered creativity accessible for developers, designers, and artists. It allows users to:
- ✍️ Write a text prompt
- 🔧 Choose a diffusion model
- 🖼️ Generate an image
- 💾 Download the result
- Interactive text-to-image generation
- Model selection from sidebar
- Live image preview with download option
- Easy-to-use web interface with Streamlit
git clone https://github.com/edcalderin/textual-diffuser.git
cd textual-diffuserconda create -n textual_diffuser python=3.12
conda activate textual_diffusersource activate textual_diffuser # On Windowspip install -r requirements.txtpython -m streamlit run src/streamlit.py- Enter a text prompt (e.g., "a fantasy landscape with dragons").
- Select a diffusion model from the sidebar.
- Click Generate Image.
- Preview the result and click Download if you want to save it.
ruff format .
ruff check . --fixconda env remove -n textual_diffuserLinkedIn: https://www.linkedin.com/in/erick-calderin-5bb6963b/
e-mail: edcm.erick@gmail.com
Explore more of my work on Medium
I regularly share insights, tutorials, and reflections on tech, AI, and more. Your feedback and thoughts are always welcome!