Update app.py

app.py

@@ -1,60 +1,53 @@
 import gradio as gr
+import requests
 import io
 import random
 import os
 import time
-import numpy as np
-import subprocess
-import torch
 import json
-from transformers import AutoProcessor, AutoModelForCausalLM
+import base64
+from io import BytesIO
+from datetime import datetime
 from PIL import Image
+from mistralai import Mistral
 from deep_translator import GoogleTranslator
-from datetime import datetime
-from model import models
+import json
 from theme import theme
 from fastapi import FastAPI
 
 app = FastAPI()
 
 
+API_URL = "https://api-inference.huggingface.co/models/black-forest-labs/FLUX.1-dev"
 API_TOKEN = os.getenv("HF_READ_TOKEN")
 headers = {"Authorization": f"Bearer {API_TOKEN}"}
 timeout = 100
-max_images = 6
-
-def flip_image(x):
-    return np.fliplr(x)
 
-def clear():
-  return None    
+api_key = os.getenv("MISTRAL_API_KEY")
+Mistralclient = Mistral(api_key=api_key)
 
-def query(lora_id, prompt, is_negative=False, steps=28, cfg_scale=3.5, sampler="DPM++ 2M Karras", seed=-1, strength=100, width=896, height=1152):
-    if prompt == "" or prompt == 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=1024, height=1024):
+    if prompt == "" or prompt is None:
         return None
 
-    if lora_id.strip() == "" or lora_id == None:
-        lora_id = "black-forest-labs/FLUX.1-dev"
-
     key = random.randint(0, 999)
-
-    API_URL = "https://api-inference.huggingface.co/models/"+ lora_id.strip()
-
+    
     API_TOKEN = random.choice([os.getenv("HF_READ_TOKEN")])
     headers = {"Authorization": f"Bearer {API_TOKEN}"}
     
-    # prompt = GoogleTranslator(source='ru', target='en').translate(prompt)
-    # print(f'\033[1mGeneration {key} translation:\033[0m {prompt}')
+    # 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}')
 
     # If seed is -1, generate a random seed and use it
     if seed == -1:
         seed = random.randint(1, 1000000000)
-
+    
     # Prepare the payload for the API call, including width and height
     payload = {
         "inputs": prompt,
@@ -69,6 +62,7 @@ def query(lora_id, prompt, is_negative=False, steps=28, cfg_scale=3.5, sampler="
         }
     }
 
+    # 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}")
@@ -76,114 +70,187 @@ def query(lora_id, prompt, is_negative=False, steps=28, cfg_scale=3.5, sampler="
         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, seed
+        return image
     except Exception as e:
         print(f"Error when trying to open the image: {e}")
         return None
-        
-with gr.Group():
-    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-12b-2409"
+        # 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"        
+
+
+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",
+]
+
+# CSS to style the app
 css = """
-footer{display:none !important}
+.gradio-container {background-color: MediumAquaMarine}
 #app-container {
     max-width: 930px;
     margin-left: auto;
     margin-right: auto;
+}
+footer {
+    visibility: hidden;
+}
 """
 
-with gr.Blocks(theme=theme, fill_width=True, css=css) as app:
-    with gr.Tab("Image Generator"):
+# Gradio Interface
+
+with gr.Blocks(css=css, theme=theme) as app:
+    gr.HTML("<h1><center>Flux Lab</center></h1>")
+    with gr.Tab(label="Image To Flux Prompt"):
         with gr.Row():
-            with gr.Column(scale=10, elem_id="prompt-container"): 
-                with gr.Group():
-                    with gr.Row(equal_height=True):
-                        text_prompt = gr.Textbox(label="Image Prompt ✍️", placeholder="Enter a prompt here", lines=2, show_copy_button = True, elem_id="prompt-text-input")
-                    with gr.Row():
-                        with gr.Accordion("🎨 Lora trigger words", open=False):
-                            gr.Markdown("""
-                                        - **Canopus-Pencil-Art-LoRA**: Pencil Art
-                                        - **Flux-Realism-FineDetailed**: Fine Detailed
-                                        - **Fashion-Hut-Modeling-LoRA**: Modeling
-                                        - **SD3.5-Large-Turbo-HyperRealistic-LoRA**: hyper realistic
-                                        - **Flux-Fine-Detail-LoRA**: Super Detail
-                                        - **SD3.5-Turbo-Realism-2.0-LoRA**: Turbo Realism
-                                        - **Canopus-LoRA-Flux-UltraRealism-2.0**: Ultra realistic 
-                                        - **Canopus-Pencil-Art-LoRA**: Pencil Art
-                                        - **SD3.5-Large-Photorealistic-LoRA**: photorealistic
-                                        - **Flux.1-Dev-LoRA-HDR-Realism**: HDR
-                                        - **prithivMLmods/Ton618-Epic-Realism-Flux-LoRA**: Epic Realism
-                                        - **john-singer-sargent-style**: John Singer Sargent Style
-                                        - **alphonse-mucha-style**: Alphonse Mucha Style
-                                        - **ultra-realistic-illustration**: ultra realistic illustration
-                                        - **eye-catching**: eye-catching
-                                        - **john-constable-style**: John Constable Style
-                                        - **film-noir**: in the style of FLMNR
-                                        - **flux-lora-pro-headshot**: PROHEADSHOT
-                            		""")
-                            
-                        with gr.Row():
-                            custom_lora = gr.Dropdown([" ", "prithivMLmods/Canopus-Pencil-Art-LoRA", "prithivMLmods/Flux-Realism-FineDetailed", "prithivMLmods/Fashion-Hut-Modeling-LoRA", "prithivMLmods/SD3.5-Large-Turbo-HyperRealistic-LoRA", "prithivMLmods/Flux-Fine-Detail-LoRA", "prithivMLmods/SD3.5-Turbo-Realism-2.0-LoRA", "hugovntr/flux-schnell-realism", "fofr/sdxl-deep-down", "prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0", "prithivMLmods/Canopus-Realism-LoRA", "prithivMLmods/Canopus-LoRA-Flux-FaceRealism", "prithivMLmods/SD3.5-Large-Photorealistic-LoRA", "prithivMLmods/Flux.1-Dev-LoRA-HDR-Realism", "prithivMLmods/Ton618-Epic-Realism-Flux-LoRA", "KappaNeuro/john-singer-sargent-style", "KappaNeuro/alphonse-mucha-style", "ntc-ai/SDXL-LoRA-slider.ultra-realistic-illustration", "ntc-ai/SDXL-LoRA-slider.eye-catching", "KappaNeuro/john-constable-style", "dvyio/flux-lora-film-noir", "dvyio/flux-lora-pro-headshot"], label="Custom LoRA",)
-                        with gr.Row():
-                            with gr.Accordion("⚙️ Advanced Settings", open=False, elem_id="settings-container"):
-                                negative_prompt = gr.Textbox(label="Negative Prompt", lines=5, 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")
-                                with gr.Row():
-                                    width = gr.Slider(label="Image Width", value=896, minimum=64, maximum=1216, step=32)
-                                    height = gr.Slider(label="Image Height", value=1152, minimum=64, maximum=1216, step=32)
-                                strength = gr.Slider(label="Prompt Strength", value=100, minimum=0, maximum=100, step=1)    
-                                steps = gr.Slider(label="Sampling steps", value=50, minimum=1, maximum=100, step=1)
-                                cfg = gr.Slider(label="CFG Scale", value=3.5, minimum=1, maximum=20, step=0.5)
-                                seed = gr.Slider(label="Seed", value=-1, minimum=-1, maximum=1000000000, step=1)                           
-                                method = gr.Radio(label="Sampling method", value="DPM++ 2M Karras", choices=["DPM++ 2M Karras", "DPM++ 2S a Karras", "DPM2 Karras", "DPM2 a Karras", "DPM++ SDE Karras", "DPM Adaptive", "DPM++ 2M", "DPM2 Ancestral", "DPM++ S", "DPM++ SDE", "DDPM", "DPM Fast", "dpmpp_2s_ancestral",  "DEIS", "DDIM", "Euler CFG PP", "Euler", "Euler a", "Euler Ancestral", "Euler+beta", "Heun", "Heun PP2", "LMS", "LMS Karras", "PLMS", "UniPC", "UniPC BH2"])
-                        with gr.Row():
-                            with gr.Accordion("🫘Seed", open=False):
-                                seed_output = gr.Textbox(label="Seed Used", elem_id="seed-output")
-                        with gr.Row(equal_height=True):
-                            with gr.Accordion("🫘Seed", open=False):
-                                seed_output = gr.Textbox(label="Seed Used", elem_id="seed-output")
-                    with gr.Row(equal_height=True):
-                        image_num = gr.Slider(label="Number of images", minimum=1, maximum=max_images, value=1, step=1, interactive=True, scale=2)
-                    # Add a button to trigger the image generation    
-                with gr.Row(equal_height=True):
-                    text_button = gr.Button("Generate Image 🎨", variant='primary', elem_id="gen-button")
-                    clear_prompt =gr.Button("Clear Prompt 🗑️",variant="primary", elem_id="clear_button")
-                    clear_prompt.click(lambda: (None), None, [text_prompt], queue=False, show_api=False)
-
-                with gr.Column(scale=10): 
-                    with gr.Group():
-                        with gr.Row():
-                            image_output = gr.Image(type="pil", label="Image Output", format="png", show_share_button=False, elem_id="gallery")
-    
-                    with gr.Group():
-                        with gr.Row():
-                            gr.Examples(
-                                examples = examples,
-                                inputs = [text_prompt],
-                            )
+            with gr.Column(scale=4):
+                input_img = gr.Image(label="Input Picture",height=520, 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)
     
-                    with gr.Group(): 
-                        with gr.Row():
-                            clear_results = gr.Button(value="Clear Image 🗑️", variant="primary", elem_id="clear_button")
-                            clear_results.click(lambda: (None), None, [image_output], queue=False, show_api=False)
-                        
-                    text_button.click(query, inputs=[custom_lora, text_prompt, negative_prompt, steps, cfg, method, seed, strength, width, height], outputs=[image_output, seed_output])
+    submit_btn.click(feifeichat, [input_img], [output_text])
 
-    app.queue(default_concurrency_limit=200, max_size=200)  # <-- Sets up a queue with default parameters
-    if __name__ == "__main__":
-        timeout = 100
-        app.launch(show_api=False, share=False)
-        
+    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)