enchanted-bagan-small

Enchanted-bagan-small is a latent text-to-image diffusion model designed to generate Bagan images based on the text input. The quality of the generated pictures heavily relies on the input prompt.

What is Bagan?

Bagan is an ancient city located in the Mandalay Region of Myanmar (formerly Burma). It was the capital of the Kingdom of Pagan from the 9th to the 13th centuries. Bagan is renowned for its vast archaeological site, which features over 2,000 well-preserved Buddhist temples, pagodas, and monasteries spread across the area. These structures were built during the height of the Kingdom of Pagan's power when it was a center of Theravada Buddhism and a major cultural and religious hub in Southeast Asia.

The temples and pagodas in Bagan are notable for their architectural beauty, intricate designs, and historical significance. They range from small, simple structures to towering monuments adorned with elaborate carvings and artwork. Bagan's landscape, with its numerous temples dotting the horizon, is particularly stunning during sunrise and sunset, drawing visitors from around the world to witness the breathtaking views.

In 2019, Bagan was designated as a UNESCO World Heritage Site, recognizing its outstanding universal value and cultural significance. Despite facing challenges such as natural disasters and modern development pressures, Bagan remains one of Myanmar's most iconic and cherished historical destinations.

Why did we choose to do this?

When we prompted the stable diffusion model to generate an image of Bagan, it produced an image depicting a pagoda from Thailand.
Hence, our decision was to fine-tune the current stable diffusion model using a multitude of Bagan photos in order to attain a clearer outcome.

How to create prompts:

When we create prompt for bagan, we have to consider 6 keywords. Those are Subject, Medium, Style, Art-sharing website, Resolution, and Additional details.

Subject -> What you want to see in the picture is the subject. Not writing enough about the subjects is a common error.

Medium -> The medium is the substance that artists work with. Illustration, oil painting, 3D rendering, and photography are a few examples. The impact of Medium is significant because a single keyword can significantly alter the style.

Style -> The image's artistic style is referred to as the style. Pop art, impressionist, and surrealist are a few examples.

Art-sharing website -> Specialty graphic websites like Deviant Art and Artstation compile a large number of images from various genres. One surefire way to direct the image toward these styles is to use them as a prompt.

Resolution -> Resolution represents how sharp and detailed the image is

Additional Details -> Sweeteners added to an image are additional details. To give the image a more dystopian and sci-fi feel, we will add those elements.

The example prompt for general bagan is: bagan, a creepy and eery Halloween setting, with Jack o lanterns on the street and shadow figures lurking about, dynamic lighting, photorealistic fantasy concept art, stunning visuals, creative, cinematic, ultra detailed, trending on art station, spooky vibe. That prompt gives you the Halloween theme.

Contributors:

Main Contributor: Ye Bhone Lin

Supervisor: Sa Phyo Thu Htet

Contributors: Thant Htoo San, Min Phone Thit

Limitation:

We can't generate a photo of a human.

Other Work:

Note: These other works are not included in this version.

Other Work: In our exploration of image generation, we also have worked into the architectural marvels of Myanmar, featuring iconic landmarks such as Ananda, Shwezigon, Bupaya, Thatbyinnyu, and Mraukoo. Each structure stands as a testament to the rich cultural and historical tapestry of the region, captured through the lens of our innovative text-to-image generator, General Bagan.

Cite As:

@misc{enchanted-bagan-small,
  author = {{Ye Bhone Lin, Sa Phyo Thu Htet}},
  title = {enchanted-bagan-small},
  url = {https://huggingface.co/Simbolo-Servicio/enchanted-bagan-small},
  urldate = {2024-1-25},
  date = {2024-1-25}
}

References:

Wikipedia (2022). Stable Diffusion. Retrieved From: https://en.wikipedia.org/wiki/Stable_Diffusion

Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-Resolution Image Synthesis with Latent Diffusion Models. Retrieved From: https://arxiv.org/abs/2112.10752

Naomi Brown (2022). What is Stable Diffusion and How to Use it. Retrieved From: https://www.fotor.com/blog/what-is-stable-diffusion

Mishra, O. (June, 9). Stable Diffusion Explained. Medium. https://medium.com/@onkarmishra/stable-diffusion-explained-1f101284484d