LuckyPlay7/lucky-poodle-lora

Lucky Poodle — SDXL DreamBooth LoRA

A LoRA fine-tuned on Lucky, a real poodle dog, using DreamBooth on Stable Diffusion XL.

Trigger word

Use the token sks poodle dog in your prompt to activate the LoRA.

Training details

Parameter	Value
Base model	stabilityai/stable-diffusion-xl-base-1.0
Training images	69 photos
Resolution	512 × 512
Epochs	30
LoRA rank	8
Mixed precision	fp16
Learning rate	1e-4
Trigger word	sks poodle dog

How to use

diffusers

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16,
)
pipe.load_lora_weights("YOUR_USERNAME/lucky-poodle-lora")
pipe = pipe.to("cuda")

image = pipe(
    "a photo of sks poodle dog sitting in front of the Eiffel Tower in Paris",
    num_inference_steps=50,
    guidance_scale=7.5,
    cross_attention_kwargs={"scale": 0.85},
).images[0]

image.save("lucky_paris.png")

ComfyUI / AUTOMATIC1111

1. Download pytorch_lora_weights.safetensors
2. Place in your models/Lora/ folder
3. Use trigger word sks poodle dog in your prompt
4. Set LoRA weight to 0.85

Example prompts

a photo of sks poodle dog wearing a red beret in Paris, photorealistic, 8k
a photo of sks poodle dog on a tropical beach in Thailand, photorealistic, 8k
a photo of sks poodle dog near the Great Pyramids of Giza, photorealistic, 8k

License

CreativeML Open RAIL-M