Downloads · 30 days
0
alibidaran/LORA_SDX-1.5-Fashion_inpainting
LORA_SDX-1.5-Fashion_inpainting is a text-to-image model from alibidaran. Use it when you need an image from a text prompt. The card lists the license as apache-2.0.
This model is the inpainting version of SDX trained on inpainting fashion dataset.
Downloads · 30 days
0
Access
Public
Updated Sep 29, 2025
Repo size
52.1 MB
Likes
0
Public
Click a slice to open those files.
.safetensors51.1 MB · 98%
From the Hugging Face model README
This model is the inpainting version of SDX trained on inpainting fashion dataset.

The code below is for the direct usage and controlling the model for making a more cohesive image based on the given prompt.
from diffusers import StableDiffusionInpaintPipeline
pipe = StableDiffusionInpaintPipeline.from_pretrained(
args.pretrained_model_name_or_path,
torch_dtype=torch.float16
).to('cuda')
pipe.load_lora_weights("out/pytorch_lora_weights.safetensors")
def generate(pipeline, prompt,image,mask,seed):
generator = torch.Generator(device='cuda').manual_seed(seed)
return pipeline(prompt=prompt,image=image,mask_image=mask,num_inference_steps=50, generator=generator).images[0]
prmot=' black and white, patterned tank top with a relaxed fit, short sleeves, and an untucked style. The blouse is hip-length, made of cotton, and has a crew neckline.'
generate(pipeline=pipe,prompt=prmot,image=sample['image'],mask=sample['mask'],seed=42)