LoRA text2image fine-tuning - Harshgarg12/LoRA_Peft_SD_Myntra_Shoes

These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were fine-tuned on the Harshgarg12/myntra_shoes_dataset dataset. You can find some example images in the following.

Intended uses & limitations

How to use

model_path = "Harshgarg12/LoRA_Peft_SD_Myntra_Shoes"
pipe_lora = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
pipe_lora.load_lora_weights("Harshgarg12/LoRA_Peft_SD_Myntra_Shoes")
pipe_lora.to(device)

prompt = "Men White Mesh Running Non-Marking Shoes. A pair of white shoes, has regular Styling, lace-ups detail, Upper, Cushioned footbed, Textured and patterned outsole, Warranty: 28 days,. Sport: Running, Material: Mesh, Fastening: Lace-Ups, Ankle Height: Regular, Outsole Type: Non-Marking, Cleats: No Cleats, Pronation for Running Shoes: Neutral, Cushioning: High."

image_lora = pipe_lora(prompt, num_inference_steps=30).images[0]

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]