Update app.py

app.py

@@ -2,15 +2,11 @@ import gradio as gr
 import numpy as np
 import random
 import os
+import requests
 
 # Fetch the API token from environment variable
 hf_token = os.getenv("HF_TOKEN")
-
-# Load the model from Hugging Face Inference API
-interface = gr.load("models/ZB-Tech/Text-to-Image", token=hf_token)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
+API_URL = "https://api-inference.huggingface.co/models/ZB-Tech/Text-to-Image"
 
 def infer(
     prompt,
@@ -24,22 +20,17 @@ def infer(
     progress=gr.Progress(track_tqdm=True),
 ):
     if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
+        seed = random.randint(0, np.iinfo(np.int32).max)
 
-    # Call the interface with the correct key ("inputs" instead of "prompt")
-    # Start with minimal parameters and add others if supported
-    image = interface(inputs=prompt)
+    headers = {"Authorization": f"Bearer {hf_token}"}
+    payload = {"inputs": prompt}  # Start with minimal payload
+    response = requests.post(API_URL, headers=headers, json=payload)
 
-    # If the model supports additional parameters, you can extend this:
-    # image = interface(
-    #     inputs=prompt,
-    #     negative_prompt=negative_prompt if negative_prompt else None,
-    #     seed=seed,
-    #     width=width,
-    #     height=height,
-    #     guidance_scale=guidance_scale,
-    #     num_inference_steps=num_inference_steps,
-    # )
+    if response.status_code != 200:
+        raise Exception(f"API Error: {response.status_code} - {response.text}")
+
+    # Assuming the response is an image (binary data)
+    image = response.content  # Gradio will handle binary image data
 
     return image, seed
 
@@ -73,73 +64,11 @@ with gr.Blocks(css=css) as demo:
 
         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=True,
-            )
-
-            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=512,
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=1.0,
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=10,
-                )
-
-        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],
+        inputs=[prompt],
+        outputs=[result],
     )
 
 if __name__ == "__main__":