Update app.py

app.py

@@ -1,154 +1,56 @@
 import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
+from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
 import torch
+import os
 
-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
-
+# --- Configuration ---
+MODEL_ID = "benisonjac/stable-diffusion-finetune"
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+DTYPE = torch.float16 if torch.cuda.is_available() else torch.float32
 
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
+# --- Load a new, more stable scheduler from the model's config ---
+scheduler = DPMSolverMultistepScheduler.from_pretrained(MODEL_ID, subfolder="scheduler")
 
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
+# --- Load the Pipeline ---
+print(f"Loading full fine-tuned model from {MODEL_ID}...")
 
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
+# Load the entire pipeline from your repository and inject the new scheduler
+pipe = DiffusionPipeline.from_pretrained(
+    MODEL_ID,
+    torch_dtype=DTYPE,
+    scheduler=scheduler,
+).to(DEVICE)
 
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
+print("Model loaded successfully.")
+pipe.unet.eval()
 
-            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=[
+# --- Define the Generation Function ---
+def generate(prompt, guidance_scale=7.5, num_steps=50):
+    with torch.no_grad():
+        image = pipe(
             prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
-
-if __name__ == "__main__":
-    demo.launch()
+            guidance_scale=guidance_scale,
+            num_inference_steps=int(num_steps)
+        ).images[0]
+    return image
+
+# --- Create the Gradio Interface ---
+demo = gr.Interface(
+    fn=generate,
+    inputs=[
+        gr.Textbox(label="Prompt", value="a photo of a high-top sneaker, futuristic design"),
+        gr.Slider(minimum=1, maximum=20, step=0.5, value=7.5, label="Guidance Scale"),
+        gr.Slider(minimum=10, maximum=100, step=1, value=50, label="Inference Steps")
+    ],
+    outputs=gr.Image(type="pil"),
+    title="Generative AI Shoe Generator",
+    description="Enter a prompt to generate a unique shoe design using a fully fine-tuned Stable Diffusion model.",
+    allow_flagging="never",
+    examples=[
+        ["a photo of a running shoe, vibrant colors", 7.5, 50],
+        ["a photo of a leather boot, classic style", 8.0, 60],
+    ]
+)
+
+# --- Launch the App ---
+demo.launch(share=True, debug=True)