Update app.py

app.py

@@ -1,58 +1,154 @@
-import os
-import gradio as gr
+import gradio as gr 
+import numpy as np
+import random
+
+# import spaces #[uncomment to use ZeroGPU]
+from diffusers import DiffusionPipeline
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
-
-# Load the Hugging Face API token from environment variable
-token = os.getenv("HUGGINGFACE_API_TOKEN")
-if not token:
-    raise ValueError("HUGGINGFACE_API_TOKEN is not set. Please add it in the Secrets section of your Space.")
-
-# Configure device
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-# Load the tokenizer and model using the token
-model_repo = "unsloth/llama-3.2-3b-instruct-bnb-4bit"
-tokenizer = AutoTokenizer.from_pretrained(model_repo, token=token)
-
-# Configure 4-bit quantization
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_compute_dtype=torch.float16
-)
-
-# Load the model with quantization configuration
-model = AutoModelForCausalLM.from_pretrained(
-    model_repo,
-    token=token,
-    device_map="auto",
-    quantization_config=quantization_config
-)
-
-# Ensure the model is in evaluation mode
-model.eval()
-
-# Define the inference function
-def infer(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt").to(device)
-    with torch.no_grad():
-        outputs = model.generate(**inputs, max_length=512)
-    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return generated_text
-
-# Gradio interface
-with gr.Blocks() as demo:
-    gr.Markdown("## LLaMA 3.2 3B Instruct Model Inference")
-
-    with gr.Row():
-        prompt = gr.Textbox(label="Prompt", placeholder="Enter your prompt here...")
-        generate_button = gr.Button("Generate")
-
-    output = gr.Textbox(label="Generated Text")
-
-    generate_button.click(fn=infer, inputs=[prompt], outputs=[output])
+
+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;
+}
+"""
+
+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],
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()