ddpm-robin-old

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

House plans

#trained on:WhiteCase

Model Details

@dataclass
class TrainingConfig:
    image_size = 512  # the generated image resolution
    train_batch_size = 2
    eval_batch_size = 2  # how many images to sample during evaluation
    num_epochs = 100
    gradient_accumulation_steps = 1
    learning_rate = 1e-4
    lr_warmup_steps = 500
    save_image_epochs = 10
    save_model_epochs = 30
    mixed_precision = 'fp16'  # `no` for float32, `fp16` for automatic mixed precision
    output_dir = 'ddpm-butterflies-128'  # the model namy locally and on the HF Hub
    push_to_hub = True  # whether to upload the saved model to the HF Hub
    hub_private_repo = False  
    overwrite_output_dir = True  # overwrite the old model when re-running the notebook
    seed = 0

config = TrainingConfig()

copy/paste/save as inference.py

from diffusers import DiffusionPipeline
import argparse

# Parse command line arguments
parser = argparse.ArgumentParser(description='Generate an image using a Hugging Face diffusion model')
parser.add_argument('--model', type=str, default="uisikdag/ddpm-few-shot-art-painting", 
                    help='Hugging Face model name/path')
parser.add_argument('--steps', type=int, default=500, 
                    help='Number of inference steps')
args = parser.parse_args()

# Load the model
generator = DiffusionPipeline.from_pretrained(args.model).to("cuda")

# Generate image
image = generator(num_inference_steps=args.steps).images[0]

# Save the image with model name in the filename
output_filename = f"output_{args.model.split('/')[-1]}.png"
image.save(output_filename)
print(f"Image saved as {output_filename}")

python inference.py --model="uisikdag/ddpm-robin-old" --steps 1000