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("PSJJ/project")
prompt = "Please generate a realistic human image with clear facial features, natural body proportions, and diverse poses. The generated person should resemble a genuine photograph with realistic lighting, clothing, and background. Pay attention to details like facial expressions, hair, and skin texture. Thank you!"
image = pipe(prompt).images[0]LoRA DreamBooth - PSJJ/project
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on Please generate a realistic human image with clear facial features, natural body proportions, and diverse poses. The generated person should resemble a genuine photograph with realistic lighting, clothing, and background. Pay attention to details like facial expressions, hair, and skin texture. Thank you! using DreamBooth. You can find some example images in the following.
LoRA for the text encoder was enabled: True.
- Downloads last month
- 3
Model tree for PSJJ/project
Base model
runwayml/stable-diffusion-v1-5