Update app.py

app.py

@@ -1,175 +1,24 @@
-import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
+from diffusers import StableDiffusionPipeline
 import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-# Force model to use float32 to avoid dtype mismatch
-torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-
-# Explicitly convert submodules to float32 to prevent dtype mismatch
-pipe.to(device)
-pipe.text_encoder.to(device, dtype=torch.float32)
-pipe.vae.to(device, dtype=torch.float32)
-pipe.unet.to(device, dtype=torch.float32)
-
-def force_float32(model):
-    for param in model.parameters():
-        param.data = param.data.to(torch.float32)
-    for buffer in model.buffers():
-        buffer.data = buffer.data.to(torch.float32)
-
-force_float32(pipe.text_encoder)
-force_float32(pipe.vae)
-force_float32(pipe.unet)
-
-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(device).manual_seed(int(seed))
-
-    # Ensure text inputs are strings
-    prompt = str(prompt) if prompt else ""
-    negative_prompt = str(negative_prompt) if negative_prompt else ""
-
-    # Ensure text input IDs are of type LongTensor
-    if isinstance(prompt, torch.Tensor):
-        prompt = prompt.to(torch.long).tolist()
-    if isinstance(negative_prompt, torch.Tensor):
-        negative_prompt = negative_prompt.to(torch.long).tolist()
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=float(guidance_scale),
-        num_inference_steps=int(num_inference_steps),
-        width=int(width),
-        height=int(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,
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,
-                )
-
-        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],
-    )
+from flask import Flask, request, jsonify
+
+app = Flask(__name__)
+
+# Load the model
+model_id = "ZB-Tech/Text-to-Image"
+pipeline = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipeline.to("cuda" if torch.cuda.is_available() else "cpu")
+
+@app.route("/generate", methods=["POST"])
+def generate_image():
+    data = request.get_json()
+    prompt = data.get("prompt", "A scenic landscape")
+    
+    image = pipeline(prompt).images[0]
+    image_path = "generated_image.png"
+    image.save(image_path)
+    
+    return jsonify({"image_url": image_path})
 
 if __name__ == "__main__":
-    demo.launch()
+    app.run(host="0.0.0.0", port=7860)