Create app.py

app.py

@@ -0,0 +1,251 @@
+import gradio as gr
+import io
+import random
+import time
+import json
+import base64
+import requests
+import os
+from mistralai import Mistral
+from PIL import Image
+from io import BytesIO
+from deep_translator import GoogleTranslator
+from datetime import datetime
+from theme import theme
+from fastapi import FastAPI
+
+app = FastAPI()
+
+API_URL = "https://api-inference.huggingface.co/models/stabilityai/stable-diffusion-3.5-large"
+API_TOKEN = os.getenv("HF_READ_TOKEN")
+headers = {"Authorization": f"Bearer {API_TOKEN}"}
+timeout = 100
+
+api_key = os.getenv("MISTRAL_API_KEY")
+Mistralclient = Mistral(api_key=api_key)
+
+def flip_image(x):
+    return np.fliplr(x)
+
+def clear():
+    return None 
+   
+
+# Function to query the API and return the generated image
+def query(prompt, is_negative=False, steps=35, cfg_scale=7, sampler="DPM++ 2M Karras", seed=-1, strength=0.7, width=896, height=1152):
+    if prompt == "" or prompt is None:
+        return None
+
+    key = random.randint(0, 999)
+    
+    API_TOKEN = random.choice([os.getenv("HF_READ_TOKEN")])
+    headers = {"Authorization": f"Bearer {API_TOKEN}"}
+    
+    # Translate the prompt from Russian to English if necessary
+    prompt = GoogleTranslator(source='ru', target='en').translate(prompt)
+    print(f'\033[1mGeneration {key} translation:\033[0m {prompt}')
+
+    # Add some extra flair to the prompt
+    prompt = f"{prompt} | ultra detail, ultra elaboration, ultra quality, perfect."
+    print(f'\033[1mGeneration {key}:\033[0m {prompt}')
+    
+    # Prepare the payload for the API call, including width and height
+    payload = {
+        "inputs": prompt,
+        "is_negative": is_negative,
+        "steps": steps,
+        "cfg_scale": cfg_scale,
+        "seed": seed if seed != -1 else random.randint(1, 1000000000),
+        "strength": strength,
+        "parameters": {
+            "width": width,  # Pass the width to the API
+            "height": height  # Pass the height to the API
+        }
+    }
+
+    # Send the request to the API and handle the response
+    response = requests.post(API_URL, headers=headers, json=payload, timeout=timeout)
+    if response.status_code != 200:
+        print(f"Error: Failed to get image. Response status: {response.status_code}")
+        print(f"Response content: {response.text}")
+        if response.status_code == 503:
+            raise gr.Error(f"{response.status_code} : The model is being loaded")
+        raise gr.Error(f"{response.status_code}")
+    
+    try:
+        # Convert the response content into an image
+        image_bytes = response.content
+        image = Image.open(io.BytesIO(image_bytes))
+        print(f'\033[1mGeneration {key} completed!\033[0m ({prompt})')
+        return image
+    except Exception as e:
+        print(f"Error when trying to open the image: {e}")
+        return None
+
+examples = [
+    "a beautiful woman with blonde hair and blue eyes",
+    "a beautiful woman with brown hair and grey eyes",
+    "a beautiful woman with black hair and brown eyes",
+]
+
+def encode_image(image_path):
+    """Encode the image to base64."""
+    try:
+        # Open the image file
+        image = Image.open(image_path).convert("RGB")
+
+        # Resize the image to a height of 512 while maintaining the aspect ratio
+        base_height = 512
+        h_percent = (base_height / float(image.size[1]))
+        w_size = int((float(image.size[0]) * float(h_percent)))
+        image = image.resize((w_size, base_height), Image.LANCZOS)
+
+        # Convert the image to a byte stream
+        buffered = BytesIO()
+        image.save(buffered, format="JPEG")
+        img_str = base64.b64encode(buffered.getvalue()).decode("utf-8")
+
+        return img_str
+    except FileNotFoundError:
+        print(f"Error: The file {image_path} was not found.")
+        return None
+    except Exception as e:  # Add generic exception handling
+        print(f"Error: {e}")
+        return None
+
+def feifeichat(image):
+    try:
+        model = "pixtral-large-2411"
+        # Define the messages for the chat
+        base64_image = encode_image(image)
+        messages = [{
+            "role":
+            "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "Please provide a detailed description of this photo"
+                },
+                {
+                    "type": "image_url",
+                    "image_url": f"data:image/jpeg;base64,{base64_image}" 
+                },
+            ],
+            "stream": False,
+        }]
+    
+        partial_message = ""
+        for chunk in Mistralclient.chat.stream(model=model, messages=messages):
+            if chunk.data.choices[0].delta.content is not None:
+                partial_message = partial_message + chunk.data.choices[
+                    0].delta.content
+                yield partial_message
+    except Exception as e:  # 添加通用异常处理
+        print(f"Error: {e}")
+        return "Please upload a photo"
+
+# CSS to style the app
+css = """
+.gradio-container {background-color: MediumAquaMarine}
+footer{display:none !important}
+#app-container {
+    max-width: 930px;
+    margin-left: auto;
+    margin-right: auto;
+}
+"""        
+
+# Build the Gradio UI with Blocks
+with gr.Blocks(theme=theme, css=css) as app:
+    # Add a title to the app
+    gr.HTML("<center><h1>🎨 Stable Diffusion 3.5 Large + 🇬🇧</h1></center>")
+        with gr.Tab(label="Image To Flux Prompt"):
+        with gr.Row():
+            with gr.Column(scale=4):
+                input_img = gr.Image(label="Input Picture",height=320, type="filepath")
+                
+            with gr.Column(scale=3):
+                output_text = gr.Textbox(label="Flux Prompt", lines=2, scale=6, show_copy_button = True)
+                submit_btn = gr.Button(value="Generate Pompt", scale=4, variant='primary')
+                clear_prompt =gr.Button("Clear 🗑️",variant="primary", elem_id="clear_button")
+                clear_prompt.click(lambda: (None, None), None, [input_img, output_text], queue=False, show_api=False)
+    
+    submit_btn.click(feifeichat, [input_img], [output_text])
+    
+with gr.Tab(label="Generate Image"):
+        with gr.Row():
+            with gr.Column(scale=4):
+                with gr.Row():
+                    img_output = gr.Image(type="pil", label="Image Output", show_share_button=False, format="png", elem_id="gallery")
+                with gr.Row():
+                    text_prompt = gr.Textbox(label="Image Prompt ✍️", placeholder="Enter prompt...", lines=2, scale=6, show_copy_button = True, elem_id="prompt-text-input")
+                    text_button = gr.Button("Generate Image",scale=1, variant='primary', elem_id="gen-button")
+                    clear_prompt =gr.Button("Clear 🗑️",variant="primary", elem_id="clear_button")
+                    clear_prompt.click(lambda: (None, None), None, [text_prompt, img_output], queue=False, show_api=False)
+            with gr.Accordion("Advanced Options", open=True):
+                with gr.Column(scale=1):
+                negative_prompt = gr.Textbox(label="Negative Prompt", placeholder="What should not be in the image", value="( (((hands:-1.25))), physical-defects:2, unhealthy-deformed-joints:2, unhealthy-hands:2, out of frame, (((bad face))), (bad-image-v2-39000:1.3), (((out of frame))), deformed body features,  (((poor facial details))), (poorly drawn face:1.3), jpeg artifacts, (missing arms:1.1), (missing legs:1.1), (extra arms:1.2), (extra legs:1.2), [asymmetrical features], warped expressions, distorted eyes ", lines=6, elem_id="negative-prompt-text-input")
+                     width = gr.Slider(
+                        label="Width",
+                        minimum=512,
+                        maximum=1280,
+                        step=8,
+                        value=896,
+                    )
+                    height = gr.Slider(
+                        label="Height",
+                        minimum=512,
+                        maximum=1280,
+                        step=8,
+                        value=1152,
+                    )
+                    method = gr.Dropdown(label="Sampling method", value="DPM++ 2M Karras", choices=["DPM++ 2M Karras", "DPM++ 2S a Karras", "DPM2 a Karras", "DPM2 Karras", "DPM++ SDE Karras", "DEIS", "LMS", "DPM Adaptive", "DPM++ 2M", "DPM2 Ancestral", "DPM++ S", "DPM++ SDE", "DDPM", "DPM Fast", "dpmpp_2s_ancestral", "Euler", "Euler CFG PP", "Euler a", "Euler Ancestral", "Euler+beta", "Heun", "Heun PP2", "DDIM", "LMS Karras", "PLMS", "UniPC", "UniPC BH2"])
+                    steps = gr.Slider(
+                        label="Sampling steps",
+                        minimum=1,
+                        maximum=100,
+                        step=1,
+                        value=24,
+                    )
+                    cfg = gr.Slider(
+                        label="CFG Scale",
+                        minimum=3.5,
+                        maximum=7,
+                        step=0.1,
+                        value=3.5,
+                    )
+                    strength = gr.Slider(label="Strength", value=90, minimum=0, maximum=100, step=10)
+                    seed = gr.Slider(label="Seed", value=-1, minimum=-1, maximum=1000000000, step=1)
+                    
+        gr.Examples(
+            examples = examples,    
+            inputs = [text_prompt], 
+        )
+    # Bind the button to the query function with the added width and height inputs
+    text_button.click(query, inputs=[text_prompt, negative_prompt, steps, cfg, method, seed, strength, width, height], outputs=img_output)
+
+    with gr.Tab("ℹ️ Tips"):
+        with gr.Row():
+            with gr.Column():
+                gr.Markdown(
+            """
+            <div style="max-width: 650px; margin: 2rem auto; padding: 1rem; border-radius: 10px; background-color: #f0f0f0;">
+                <h2 style="float: left; font-size: 1.5rem; margin-bottom: 1rem;">How to Use</h2>
+                <ol style="padding-left: 1.5rem;">
+                    <li>Add an image to generate a prompt, this is optional.</li>
+                    <li>If using an image to prompt, copy the prompt and paste into the prompt on tab 2</li>
+                    <li>Enter a detailed description of the image you want to create.</li>
+                    <li>Adjust advanced settings if desired (tap to expand).</li>
+                    <li>Tap "Generate Image" and wait for your creation!</li>
+                </ol>
+                <p style="margin-top: 1rem; font-style: italic;">Tip: Be specific in your description for best results!</p>
+                <p style="margin-top: 1rem; font-style: italic;">*Note: Some LoRA models will not work every time (not sure why), refresh the page and try again</p>
+                <p style="margin-top: 1rem; font-style: italic;">*I'm still playing around to try to sort the issue, feel free to let me know if you find a fix</p>
+            </div>
+            """
+            )
+                
+app.queue(default_concurrency_limit=200, max_size=200)  # <-- Sets up a queue with default parameters
+if __name__ == "__main__":
+    app.launch(show_api=False, share=False)
+