Stable Diffusion model for generating images of Fjords

My family had the experience of going to the Norwegian Fjords in May 2022 and I took some great pictures on my new camera. Well now I have created a stable diffusion model that allows you to generate images of your own and get them to work with the Norweigen Fjord image set, this is located here: https://huggingface.co/datasets/StatsGary/dreambooth-hackathon-images.

Access the HuggingFace model

To access the HuggingFace model you can go directly to this link: https://huggingface.co/StatsGary/norweigen-fjords-fjords?text=a+lobster+in+the+norweigen+fjords.

Using the HuggingFace UI to generate Fjord based images

Use a prompt on the main screen to create your Fjord based images:

I provide an example prompt after the post request and this will use the model I have created to generate some funny mash ups, as below:

This has been fine tuned on a stable diffusion pipeline as part of the Dreambooth Hackathon HuggingFace are running.

A couple more examples:

Prompt = “a viking warrior on a fjord” which generates the below, or a similar type of image:

Another example would be:

Prompt = “a beetles like yellow submarines on a fjord” this results in:

I will be uploading some more models to this, so please keep an eye out for further releases. If you like the model sign up to HuggingFace and give it a like. The model card is here: https://huggingface.co/StatsGary/norweigen-fjords-fjords.

Implementing in code

To implement the model in code follow the below Gist:

Wrapping up

I really enjoyed fine tuning this model, for fun, but initially it took a while to setup. Watch this space for more model cards to come in the future.