first commit

app.py

@@ -1,154 +1,82 @@
+import torch
 import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
 from diffusers import DiffusionPipeline
-import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-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().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 = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
+from PIL import Image, ImageDraw, ImageFont
+
+# Initialize the model globally for faster inference
+pipe = None
+
+def load_model():
+    global pipe
+    if pipe is None:
+        pipe = DiffusionPipeline.from_pretrained("segmind/tiny-sd", torch_dtype=torch.float32)
+        pipe = pipe.to("cpu")
+    return pipe
+
+def generate_image_with_text(prompt, caption_text):
+    """
+    Generate an image based on a text prompt and add simple text with border at the bottom
+    """
+    # Ensure model is loaded
+    pipe = load_model()
+    
+    # Generate image
+    image = pipe(prompt, num_inference_steps=20, height=384, width=384).images[0]
+    
+    # Add space for text at bottom
+    width, height = image.size
+    new_img = Image.new("RGB", (width, height + 40), (0, 0, 0))
+    new_img.paste(image, (0, 0))
+    
+    # Add text with border
+    draw = ImageDraw.Draw(new_img)
+    
+    # Use default font
+    font = ImageFont.load_default()
+    
+    # Calculate text position to center it
+    text_width = draw.textlength(caption_text, font=font)
+    text_x = (width - text_width) / 2
+    text_y = height + 10
+    
+    # Draw text border (offset in 4 directions)
+    offset = 1  # Border thickness
+    for dx, dy in [(-offset, -offset), (-offset, offset), (offset, -offset), (offset, offset),
+                  (0, -offset), (0, offset), (-offset, 0), (offset, 0)]:
+        draw.text((text_x + dx, text_y + dy), caption_text, fill=(0, 0, 0), font=font)
+    
+    # Draw main text in white
+    draw.text((text_x, text_y), caption_text, fill=(255, 255, 255), font=font)
+    
+    return new_img
+
+# Create Gradio interface
+title = "Text-to-Image Generator with Caption"
+description = """
+Generate an image from a text prompt and add a caption at the bottom.
+The model used is lightweight and runs on CPU.
 """
 
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        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,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        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],
-    )
-
+demo = gr.Interface(
+    fn=generate_image_with_text,
+    inputs=[
+        gr.Textbox(label="Image Prompt", placeholder="Describe the image you want to generate..."),
+        gr.Textbox(label="Caption Text", placeholder="Text to display at the bottom of the image")
+    ],
+    outputs=gr.Image(type="pil", label="Generated Image"),
+    title=title,
+    description=description,
+    examples=[
+        ["A serene mountain landscape at sunset", "Beautiful Sunset View"],
+        ["A cute cat playing with yarn", "Playful Kitten"],
+        ["Abstract colorful shapes", "Modern Art"]
+    ],
+    cache_examples=False,
+)
+
+# Load the model when the app starts
+load_model()
+
+# Launch the app
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1,6 +1,6 @@
-accelerate
-diffusers
-invisible_watermark
 torch
+diffusers
 transformers
-xformers
+gradio
+pillow
+accelerate