LoRA text2image fine-tuning - NouRed/sd-fashion-products

These are LoRA adaption weights for stabilityai/stable-diffusion-2. The weights were fine-tuned on the hahminlew/kream-product-blip-captions dataset. You can find some example images in the following.

Usage

import torch
from diffusers import DiffusionPipeline

# Load Previous Pipeline
pipeline = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-2", revision=None, variant=None, torch_dtype=torch_dtype=torch.float32
)
pipeline = pipeline.to(accelerator.device)

# Load attention processors
pipeline.unet.load_attn_procs("NouRed/sd-fashion-products")

# Run Inference
generator = torch.Generator(device=accelerator.device)
seed = 42
if seed is not None:
    generator = generator.manual_seed(seed)

prompt = "outer, The North Face x Supreme White Label Nuptse Down Jacket Cream, a photography of a white puffer jacket with a red box logo on the front."
image = pipeline(prompt, num_inference_steps=30, generator=generator).images[0]  

# Save Generated Product
image.save("red_box_jacket.png")