Update app.py

app.py

@@ -1,32 +1,68 @@
-import gradio as gr
 import torch
-import modin.pandas as pd
 import numpy as np
-from diffusers import DiffusionPipeline 
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    torch.cuda.empty_cache()
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-    torch.cuda.empty_cache()
-else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
-    
-def genie (prompt, steps, seed):
-    generator = np.random.seed(0) if seed == 0 else torch.manual_seed(seed)
-    int_image = pipe(prompt=prompt, generator=generator, num_inference_steps=steps, guidance_scale=0.0).images[0]
-    return int_image
+from flask import Flask, request, jsonify
+from diffusers import DiffusionPipeline, DDIMScheduler
+from PIL import Image
+import base64
+import io
+import gc
+import os
+
+app = Flask(__name__)
+
+# Device set to CPU and optimize threading
+device = "cpu"
+torch.set_num_threads(max(1, os.cpu_count() or 4))
+torch.set_num_interop_threads(max(1, os.cpu_count() or 4))
+
+# Load model with accelerate and disable safety checker
+pipe = DiffusionPipeline.from_pretrained(
+    "stabilityai/sdxl-turbo",
+    use_safetensors=True,
+    low_cpu_mem_usage=True
+)
+pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)  # Faster scheduler
+pipe.safety_checker = None  # Disable safety checker
+pipe = pipe.to(device)
+pipe.unet.enable_model_cpu_offload()
+
+def infer(prompt, steps=1, seed=0):
+    if not prompt or len(prompt.split()) > 77:
+        return "Prompt missing or exceeds 77 tokens!", 0
     
-gr.Interface(fn=genie, inputs=[gr.Textbox(label='What you want the AI to generate. 77 Token Limit.'), 
-    gr.Slider(1, maximum=5, value=2, step=1, label='Number of Iterations'), 
-    gr.Slider(minimum=0, step=1, maximum=999999999999999999, randomize=True),
-    ],
-    outputs='image', 
-    title="Stable Diffusion Turbo CPU or GPU", 
-    description="SDXL Turbo CPU or GPU. Currently running on CPU. <br><br><b>WARNING: This model is capable of producing NSFW (Softcore) images.</b>", 
-    article = "If You Enjoyed this Demo and would like to Donate, you can send to any of these Wallets. <br>BTC: bc1qzdm9j73mj8ucwwtsjx4x4ylyfvr6kp7svzjn84 <br>3LWRoKYx6bCLnUrKEdnPo3FCSPQUSFDjFP <br>DOGE: DK6LRc4gfefdCTRk9xPD239N31jh9GjKez <br>SHIB (BEP20): 0xbE8f2f3B71DFEB84E5F7E3aae1909d60658aB891 <br>PayPal: https://www.paypal.me/ManjushriBodhisattva <br>ETH: 0xbE8f2f3B71DFEB84E5F7E3aae1909d60658aB891 <br>Code Monkey: <a href=\"https://huggingface.co/Manjushri\">Manjushri</a>").launch(debug=True, max_threads=80)
+    generator = torch.Generator(device=device).manual_seed(seed) if seed != 0 else torch.Generator(device=device).manual_seed(np.random.randint(0, 2**32 - 1))
+
+    with torch.no_grad():
+        image = pipe(
+            prompt=prompt,
+            num_inference_steps=steps,
+            guidance_scale=0.0,
+            height=512,
+            width=512,
+            generator=generator,
+            output_type="pil",
+            num_images_per_prompt=1
+        ).images[0]
+
+    gc.collect()
+    return image, seed
+
+@app.route('/generate', methods=['POST'])
+def generate():
+    prompt = request.form.get('prompt')
+    steps = int(request.form.get('steps', 1))
+    seed = int(request.form.get('seed', 0))
+
+    result, seed_used = infer(prompt, steps, seed)
+
+    if isinstance(result, str):
+        return jsonify({'error': result, 'seed': seed_used}), 400
+
+    buffered = io.BytesIO()
+    result.save(buffered, format="PNG")
+    img_str = base64.b64encode(buffered.getvalue()).decode('utf-8')
+
+    return jsonify({'image': img_str, 'seed': seed_used})
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=8000)