CartoonFaceLora / app.py
Leofreddare's picture
Update app.py
72d2898 verified
import gradio as gr
import numpy as np
import random
from diffusers import StableDiffusionXLPipeline
import torch
from huggingface_hub import hf_hub_download
# Set device: use "cuda" if available, otherwise "cpu"
device = "cuda" if torch.cuda.is_available() else "cpu"
# Change the model to SDXL 1.0 base
model_repo_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"
if torch.cuda.is_available():
torch_dtype = torch.float16
else:
torch_dtype = torch.float32
# Load the SDXL 1.0 base pipeline with safetensors support.
pipe = StableDiffusionXLPipeline.from_pretrained(
model_repo_id,
torch_dtype=torch_dtype,
use_safetensors=True
)
pipe = pipe.to(device)
# Download your DreamCartoonLora weights from Hugging Face and load them into the pipeline.
lora_path = hf_hub_download(repo_id="Leofreddare/CartoonFaceLora", filename="CartoonFaceLora.safetensors")
print("Loaded CartoonFaceLora from:", lora_path)
pipe.load_lora_weights(lora_path)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
def infer(
prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
progress=gr.Progress(track_tqdm=True),
):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator(device=device).manual_seed(seed)
image = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
width=width,
height=height,
generator=generator,
).images[0]
return image, seed
examples = [
"A dreamy cartoon landscape with vivid colors",
"A futuristic city rendered in a cartoon style",
"A magical forest with a cartoon twist",
]
css = """
#col-container {
margin: 0 auto;
max-width: 640px;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown("# Text-to-Image with CartoonFaceLora on SDXL 1.0")
with gr.Row():
prompt = gr.Text(label="Prompt", show_label=False, max_lines=1, placeholder="Enter your prompt", container=False)
run_button = gr.Button("Run", scale=0, variant="primary")
result = gr.Image(label="Result", show_label=False)
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Text(label="Negative prompt", max_lines=1, placeholder="Enter a negative prompt", visible=False)
seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
with gr.Row():
width = gr.Slider(label="Width", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=1024)
height = gr.Slider(label="Height", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=1024)
with gr.Row():
guidance_scale = gr.Slider(label="Guidance scale", minimum=0.0, maximum=10.0, step=0.1, value=7.5)
num_inference_steps = gr.Slider(label="Inference steps", minimum=1, maximum=50, step=1, value=20)
gr.Examples(examples=examples, inputs=[prompt])
gr.on(triggers=[run_button.click, prompt.submit],
fn=infer,
inputs=[prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
outputs=[result, seed])
if __name__ == "__main__":
demo.launch()