Update app.py

app.py

@@ -1,17 +1,23 @@
+from flask import Flask, request, jsonify, send_file
+from flask_cors import CORS  # For enabling CORS
 import gradio as gr
-from random import randint
-from all_models import models
-from externalmod import gr_Interface_load
 import asyncio
 import os
 from threading import RLock
 from gradio_client import Client
+from all_models import models  # Your model import
+from externalmod import gr_Interface_load  # Your custom model loader
 
+app = Flask(__name__)
+CORS(app)  # Enable CORS for all routes
+
+# Gradio Client Initialization
 client = Client("Geek7/mdztxi2")
 
 lock = RLock()
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
+# Model Loading Function
 def load_fn(models):
     global models_load
     models_load = {}
@@ -22,17 +28,13 @@ def load_fn(models):
                 m = gr_Interface_load(f'models/{model}', hf_token=HF_TOKEN)
             except Exception as error:
                 print(error)
-                m = gr.Interface(lambda: None, ['text'], ['image'])
+                m = gr.Interface(lambda: None, ['text'], ['image'])  # Fallback
             models_load.update({model: m})
 
 load_fn(models)
 
-num_models = 6
-MAX_SEED = 3999999999
-default_models = models[:num_models]
-inference_timeout = 600
-
-async def infer(model_str, prompt, seed=1, timeout=inference_timeout):
+# Async inference function to call Gradio model prediction
+async def infer(model_str, prompt, seed=1, timeout=600):
     kwargs = {"seed": seed}
     task = asyncio.create_task(asyncio.to_thread(models_load[model_str].fn, prompt=prompt, **kwargs, token=HF_TOKEN))
     await asyncio.sleep(0)
@@ -51,19 +53,26 @@ async def infer(model_str, prompt, seed=1, timeout=inference_timeout):
         return png_path
     return None
 
-# Expose Gradio API
-def generate_api(model_str, prompt, seed=1):
-    result = asyncio.run(infer(model_str, prompt, seed))
-   # result = client.predict(
-         #   model_str=model_str,
-         #   prompt=prompt,
-        #    seed=seed,
-          #  api_name="/predict"
-#)
-    if result:
-        return result  # Path to generated image
-    return None
+# API endpoint for generating an image and sending it as a file
+@app.route('/generate-image', methods=['POST'])
+def generate_image():
+    data = request.get_json()
+    model_str = data.get('model_str')
+    prompt = data.get('prompt')
+    seed = data.get('seed', 1)
+
+    # Validate input
+    if not model_str or not prompt:
+        return jsonify({"error": "Model string and prompt are required."}), 400
+
+    # Generate image using the async inference function
+    result_path = asyncio.run(infer(model_str, prompt, seed))
+
+    if result_path:
+        # Return the image file using send_file
+        return send_file(result_path, mimetype='image/png')
+    else:
+        return jsonify({"error": "Image generation failed."}), 500
 
-# Launch Gradio API without frontend
-iface = gr.Interface(fn=generate_api, inputs=["text", "text", "number"], outputs="file", api_name="/predict")
-iface.launch(show_api=True, share=True)
+if __name__ == '__main__':
+    app.run(debug=True)