Update app.py

app.py

@@ -1,59 +1,148 @@
 import gradio as gr
-import torch
+import numpy as np
+import random
 from transformers import AutoModelForCausalLM, AutoTokenizer
-import spaces  # Make sure this is in your requirements.txt
 
-SYSTEM_PROMPT = "You are Qwen/Qwen2.5-3B-Instruct, created by Alibaba Cloud. You are a helpful assistant."
+# import spaces #[uncomment to use ZeroGPU]
+from diffusers import DiffusionPipeline
+import torch
 
-@spaces.GPU()  # ✅ Correct syntax
-def load_model():
-    model_name = "Qwen/Qwen2.5-3B-Instruct"
-    model = AutoModelForCausalLM.from_pretrained(
-        model_name,
-        torch_dtype=torch.float16,
-        device_map="auto"
-    )
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    return model, tokenizer
-
-model, tokenizer = load_model()
-
-def generate_response(user_input, history=None):
-    if history is None:
-        history = []
-    messages = [{"role": "system", "content": SYSTEM_PROMPT}]
-    for user_msg, bot_msg in history:
-        messages.append({"role": "user", "content": user_msg})
-        messages.append({"role": "assistant", "content": bot_msg})
-    messages.append({"role": "user", "content": user_input})
-    
-    prompt_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-    model_inputs = tokenizer([prompt_text], return_tensors="pt").to(model.device)
-
-    generated_ids = model.generate(
-        **model_inputs,
-        max_new_tokens=512,
-        do_sample=True,
-        temperature=0.7,
-        top_p=0.9
-    )
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model_repo_id = "Qwen/Qwen2.5-3B-Instruct"  
+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
+
+
+css = """
+#col-container {
+    margin: 0 auto;
+    max-width: 640px;
+}
+"""
 
-    new_tokens = generated_ids[0][model_inputs.input_ids.shape[-1]:]
-    response = tokenizer.decode(new_tokens, skip_special_tokens=True)
-    history.append((user_input, response))
-    return history
-
-chatbot_ui = gr.ChatInterface(
-    fn=generate_response,
-    title="🧠 Qwen 2.5 3B - Chatbot",
-    description="A simple chatbot interface powered by Qwen2.5-3B-Instruct (Alibaba Cloud).",
-    theme="soft",
-    examples=[
-        "How can virtual reality (VR) influence consumer behavior towards sustainability?",
-        "What impact does sustainable packaging have on consumer purchasing decisions?",
-        "In what ways can education promote more sustainable consumer behaviors?"
-    ],
-)
+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__":
-    chatbot_ui.launch()
+    demo.launch()