File size: 1,891 Bytes
907171e 9c99cd9 72d181d 2467efd 72d181d 383cc6f 72d181d aa165fb 72d181d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
import torch
from PIL import Image
from diffusers import StableDiffusionImg2ImgPipeline
import gradio as gr
# Load the model
model_id_or_path = "stablediffusionapi/realistic-vision-v20-2047"
device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = StableDiffusionImg2ImgPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float32).to(device)
def generate_image(content_img, style_img, prompt, guidance_scale, strength):
if content_img is None or style_img is None:
return None
content_image = Image.open(content_img).convert("RGB").resize((450, 450))
style_image = Image.open(style_img).convert("RGB").resize((450, 450))
seed_value = torch.randint(0, 4294967295, size=(1,)).item()
result = pipe(
image=content_image,
guidance=style_image,
guidance_scale=guidance_scale,
strength=strength,
num_inference_steps=100,
prompt=prompt,
seed=seed_value
).images[0]
return result
with gr.Blocks() as demo:
gr.Markdown("# Advanced Neural Style Transfer with Stable Diffusion")
with gr.Row():
content_img = gr.Image(type="filepath", label="Upload Content Image")
style_img = gr.Image(type="filepath", label="Upload Style Image")
with gr.Row():
prompt = gr.Textbox(label="Enter Stable Diffusion Prompt", placeholder="e.g., 'Van Gogh painting'")
generate_btn = gr.Button("Generate")
with gr.Row():
guidance_scale = gr.Slider(5.0, 20.0, value=16.0, label="Guidance Scale: #light (content image emphasized) 5.0 - 10.0 #haevy (style image emphasized) 15.0 - 20.0")
strength = gr.Slider(0.3, 1.0, value=0.45, label="Strength")
output_image = gr.Image(label="Generated Image")
generate_btn.click(generate_image, inputs=[content_img, style_img, prompt, guidance_scale, strength], outputs=output_image)
demo.launch()
|