Using a set of 25 mainly old large format photos from the 19th and early 20th century I wanted to capture the lighting, expression and film artifacts from this era. Subjects range in age, gender & ethnicity with poses generally looking at the camera with a neutral expression.
While only a couple of my source images had distressed frames, plenty of the generations contain them.
SD2.1 - 768 model. Trained with 6000 steps using The Last Ben.
Use oldpt as keyword.
I've also included a .yaml (click config on the download arrow) as i needed this to sit beside the checkpoint to run in the Auto1111 gui.
Hot tip : Using SoCalGuitarist's embeddings adds some extra flavor.
example prompt:
oldpt woman photograph, full body, large format, AnalogFilm768-BW-Modern
Keen to see what everyone comes up with!
Shoot me a message or reach out on to me on twitter.
Old Portraits is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user simonbronson. Derived from the powerful Stable Diffusion (SD 2.1) model, Old Portraits has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that Old Portraits is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as vintage, photorealistic, photography.
With a rating of 0 and over 0 ratings, Old Portraits is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of Old Portraits from here.
To use Old Portraits, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like Old Portraits, check out our crash course in AI image generation.