README.md

metadata

language: en
pipeline_tag: text-to-image
tags:
  - stable-diffusion
  - stable-diffusion-xl
  - text-to-image
  - diffusers
  - lora
inference: true
base_model:
  - stabilityai/stable-diffusion-3.5-large

SimpleTuner-stable-diffusion-3.5-large-ZukyTheDog

This is a custom-trained LoRA model for Stable Diffusion 3.5, focused on generating images of ZukyTheDog.

Model Description

This model is a LoRA fine-tune of Stable Diffusion 3.5, trained to generate high-quality images of ZukyTheDog. It can be used to create detailed and accurate representations in various styles and settings.

Base Model

• Base Model: Stable Diffusion 3.5

How to Use

You can use this model in two ways:

1. Using Hugging Face Inference API

Simply input your prompt in the inference API tab above and click "Compute".

Example prompts:

• "A photo of ZukyTheDog sitting in a garden"
• "ZukyTheDog playing with a ball, high quality, detailed"
• "Portrait of ZukyTheDog in a natural setting"

2. Using Python Code

from diffusers import StableDiffusion3Pipeline
import torch

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3.5-large", torch_dtype=torch.bfloat16, variant = 'fp16', use_safetensors = True)

pipe.to("cuda")
pipe.load_lora_weights("CarlosRiverMe/SimpleTuner-stable-diffusion-3.5-large-ZukyTheDog", weight_name="pytorch_lora_weights.safetensors")

prompt = "A photo of ZukyTheDog sitting in a garden"
image = pipe(prompt).images[0]
image.save("generated_image.png")