Hugging Face's logo

radames
/
sd-21-DPO-LoRA

Text-to-Image
Diffusers
Model card Files Community
sd-21-DPO-LoRA / README.md
radames's picture
radames
Update README.md
92d8540
preview code
|
raw
history blame
1.43 kB
metadata
library_name: diffusers
pipeline_tag: text-to-image
inference: true
base_model: stabilityai/sd-turbo

DPO LoRA Stable Diffusion v2-1

Model trained with LoRA implementation of Diffusion DPO Read more here

Base Model: https://huggingface.co/stabilityai/stable-diffusion-2-1

Without DPO Lora
image/png

With DPO Lora image/png

Running 

from diffusers import DiffusionPipeline
from diffusers.utils import make_image_grid
import torch

pipe = DiffusionPipeline.from_pretrained(
    "stabilityai/sd-turbo", 
    # "stabilityai/stable-diffusion-2-1",
    torch_dtype=torch.float16, variant="fp16"
)
pipe.load_lora_weights("radames/dpo-lora-sd2.1")
seed = 123123
pipe.to("cuda")
prompt = "portrait headshot professional of elon musk"
negative_prompt = "3d render, cartoon, drawing, art, low light"
generator = torch.Generator().manual_seed(seed)
images = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=512,
    height=512,
    num_inference_steps=2,
    generator=generator,
    guidance_scale=1.0,
    num_images_per_prompt=4
).images
make_image_grid(images, 1, 4)