import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("quasar529/ft-sd15-human")
prompt = "((Best quality)), ((masterpiece)), ((realistic)) human upper body photo of a person for an ID or passport. The photo will be taken with soft, even lighting in an indoor setting. The style will focus on realism, using digital photography as the medium. The artwork will depict an upper body portrait, capturing the subject in a professional attire. The color scheme will consist of neutral tones, creating a refined and polished appearance. The final result will be a high definition, precise depiction suitable for an ID or passport."
image = pipe(prompt).images[0]LoRA DreamBooth - MayIBorn/ft-sd15-human
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on ((Best quality)), ((masterpiece)), ((realistic)) human upper body photo of a person for an ID or passport. The photo will be taken with soft, even lighting in an indoor setting. The style will focus on realism, using digital photography as the medium. The artwork will depict an upper body portrait, capturing the subject in a professional attire. The color scheme will consist of neutral tones, creating a refined and polished appearance. The final result will be a high definition, precise depiction suitable for an ID or passport. using DreamBooth. You can find some example images in the following.
LoRA for the text encoder was enabled: True.
- Downloads last month
- -
Model tree for quasar529/ft-sd15-human
Base model
runwayml/stable-diffusion-v1-5