Image Generation
Collection
LoRA adapters and datasets from diffusion model research
•
9 items
•
Updated
These are LoRA DreamBooth weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using DreamBooth on the AdamLucek/green-chair Dataset.
LoRA for the text encoder was enabled: True.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
You should use a photo of sks chair to trigger the image generation.
Reference Image Generated Images on a street in new york, in a desert, in a jungle, in the color blue
Weights for this model are available in Safetensors format.
# Load Stable Diffusion XL Base 1.0
pipe = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
torch_dtype=torch.float16,
variant="fp16",
use_safetensors=True
).to("cuda")
# Optional, enable cpu offloading
pipe.enable_model_cpu_offload()
# Load LoRA Weights
pipe.load_lora_weights("AdamLucek/sdxl-base-1.0-greenchair-dreambooth-lora")
# Generate an Image
image = pipe(
prompt = "a photo of sks chair",
num_inference_steps=50,
height=1024,
width=1024,
).images[0]
# Save the Image
image.save("green_chair.png")
Note: Limited tuning of hyperparameters
Note: See original Stable Diffusion XL Base 1.0 page for additional limitations and biases
Trained using Dreambooth via Diffusers on a single A100
Training Script:
accelerate launch train_dreambooth_lora_sdxl.py \
--pretrained_model_name_or_path="stabilityai/stable-diffusion-xl-base-1.0" \
--dataset_name="AdamLucek/green-chair" \
--pretrained_vae_model_name_or_path="madebyollin/sdxl-vae-fp16-fix" \
--output_dir="lora-trained-xl" \
--train_text_encoder \
--instance_prompt="a photo of sks chair" \
--resolution=1024 \
--train_batch_size=1 \
--gradient_accumulation_steps=4 \
--learning_rate=1e-4 \
--lr_scheduler="constant" \
--lr_warmup_steps=0 \
--max_train_steps=500 \
--validation_prompt="A photo of sks chair in an apartment" \
--validation_epochs=25 \
--seed="0" \
--hub_model_id="sdxl-base-1.0-greenchair-dreambooth-lora" \
--push_to_hub
Base model
stabilityai/stable-diffusion-xl-base-1.0