Stable Diffusion:

Stable Diffusion is a generative artificial intelligence (generative AI) model that produces unique photorealistic images from text and image prompts. The model is based on diffusion technology and uses latent space. This significantly reduces processing requirements, and you can run the model on desktops or laptops equipped with GPUs. Stable Diffusion can be fine-tuned to meet your specific needs with as little as five images through transfer learning.

Model info:

The model is trained on aorund 100 images of actor Brad Pitt.
The oraul/Stability_CelebsHAQ_v1 is a Stable Diffusion model that has been fine-tuned by using stabilityai/stable-diffusion-xl-base-1.0 as a base model

Usage:

!pip install -U -qq git+https://github.com/huggingface/diffusers.git -q !pip install -qq accelerate transformers ftfy -q

!pip install transformers -q

from diffusers import StableDiffusionPipeline

import torch

model = "oraul/Stability_CelebsHAQ_v1" pipeline = StableDiffusionPipeline.from_pretrained(model, torch_dtype=torch.float16).to("cuda")

prompt = "how the personal batch2_proj_11 was looked at the age of 2 years" # here, batch2_proj_11 is the placeholder that identifies unique style in the model. please add it into the angel brackets image = pipeline(prompt).images[0]

image