ModelsLab LoRA DreamBooth Training - stablediffusionapi/my-stablediffusion-lora-2716

These are LoRA adaption weights for Lykon/DreamShaper. The weights were trained on material, mahogany, floor, interior, living room, using ModelsLab. LoRA for the text encoder was enabled: False.

Use it with the 🧨 diffusers library

!pip install -q transformers accelerate peft diffusers
from diffusers import DiffusionPipeline
import torch

pipe_id = "Lykon/DreamShaper"
pipe = DiffusionPipeline.from_pretrained(pipe_id, torch_dtype=torch.float16).to("cuda")
pipe.load_lora_weights("stablediffusionapi/my-stablediffusion-lora-2716", weight_name="pytorch_lora_weights.safetensors", adapter_name="abc")
prompt = "abc of a hacker with a hoodie"
lora_scale = 0.9
image = pipe(
    prompt,
    num_inference_steps=30,
    cross_attention_kwargs={"scale": 0.9},
    generator=torch.manual_seed(0)
).images[0]
image