Deep Dream

Deep Dream

Applies the DeepDream effect to a picture with a Keras model in a Gradio page, with a sky photo included to try. For machine learning learners and image hobbyists.

Made by keras-io 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: Deep Dream is a Gradio app that applies the DeepDream effect to a picture, by its name. DeepDream makes a neural network exaggerate the patterns it sees in an image. The record names one Keras model and includes a sky photo, sky.jpg.

Who it suits: It suits machine learning learners and image hobbyists who want to see what a vision network picks up, and developers who want a small Gradio example around a Keras model. The record has no usage notes, so the page is the guide.

Industry | Who uses it | How they use it | Example
Education | Machine learning students | See what a vision network responds to | Run the sky photo and look at the patterns
Art | Digital artists | Make dreamlike, pattern-heavy versions of pictures | Try one of your own images
Software | Python developers | Read a small Keras demo wrapped in Gradio | Open app.py and requirements.txt

You can skip it if you want a realistic photo editor, since the effect distorts images on purpose.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• Windows, macOS or Linux with Python, from a downloaded copy

Use case | Who | What they get back
Apply DeepDream to a picture | Hobbyists and artists | A pattern-rich version of the image
Study a vision model | Students | A view of what the network picks up
Reuse as a base | Developers | A small Gradio app around a Keras model

How to set it up:

• Nothing at all if you use the online Space
• Python on your computer, only if you run a copy
• The packages listed in requirements.txt

1. Open the Space's page in a browser to use it with nothing to install.
2. To run a copy, install the Hugging Face Hub package and download the Space.
3. Move into the new folder, then install Gradio and the listed requirements.
4. Start the app with Python.

pip install -U huggingface_hub
hf download keras-io/deep-dream --repo-type space --local-dir deep-dream
cd deep-dream
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Online, open the Space and use the controls on its page. On your own machine, run the main file from the Space folder, then use the page it serves. The record does not list the controls, so look at the page.

python app.py

Example: You open the Space and give it a picture, such as the included sky photo. The app returns a version where the network's favorite patterns have been amplified. The record shows no sample output, so the look depends on the page's settings.

For newcomers and experts: DeepDream asks a trained image network what it sees in a picture and then pushes the picture further toward that. Start by opening the Space and running the sky photo.

If you know the field, DeepDream runs gradient ascent on an image to raise the activations of chosen layers of a pretrained network. Which layers and how many steps the app uses is not in the record, so read app.py for that.

You give the page a picture
The app feeds it to the Keras model
Gradient steps amplify the model's patterns
The page shows the changed picture

Good to know:

• License: cc0-1, as listed on the Space
• Cost to run: none named
• Data it reaches: the pictures you give it and the model it names
• Not for: the record names no exclusions, and the effect distorts images on purpose

On Hugging Face, 13 November 2026

• Likes: 6
• Built with: gradio
• License: cc0-1.0

Links

• Space: https://huggingface.co/spaces/keras-io/deep-dream
• Files: https://huggingface.co/spaces/keras-io/deep-dream/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.