Nymbo's picture
Update app.py
c64e303 verified
import gradio as gr
import random
import os
from PIL import Image
from typing import Optional
from huggingface_hub import InferenceClient
# Project by Nymbo
API_TOKEN = os.getenv("HF_READ_TOKEN")
timeout = 100
# Function to query the API and return the generated image
def flux_krea_generate(
prompt: str,
negative_prompt: str = "(deformed, distorted, disfigured), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, misspellings, typos",
steps: int = 35,
cfg_scale: float = 7.0,
sampler: str = "DPM++ 2M Karras",
seed: int = -1,
strength: float = 0.7,
width: int = 1024,
height: int = 1024
) -> Optional[Image.Image]:
"""
Text-to-image generation with FLUX.1-Krea-dev (no input image required).
This tool generates a single image from a text prompt using the
black-forest-labs/FLUX.1-Krea-dev model on Hugging Face Inference.
Args:
prompt: Text description of the image to generate.
negative_prompt: What should NOT appear in the image.
steps: Number of denoising steps (1-100). Higher is slower but can improve quality.
cfg_scale: Classifier-free guidance scale (1-20). Higher = follow the prompt more closely.
sampler: Sampling method to use. One of: "DPM++ 2M Karras", "DPM++ SDE Karras", "Euler", "Euler a", "Heun", "DDIM".
seed: Random seed for reproducible results. Use -1 for a random seed per call.
strength: Generation strength (0-1). Kept for parity; not an input image strength.
width: Output width in pixels (64-1216, multiple of 32 recommended).
height: Output height in pixels (64-1216, multiple of 32 recommended).
Returns:
A PIL.Image of the generated result. No input image is expected or required.
"""
if prompt == "" or prompt is None:
return None
key = random.randint(0, 999)
# Add some extra flair to the prompt
enhanced_prompt = f"{prompt} | ultra detail, ultra elaboration, ultra quality, perfect."
print(f'\033[1mGeneration {key}:\033[0m {enhanced_prompt}')
try:
# Initialize the Hugging Face Inference Client
# Try different providers in order of preference
providers = ["auto", "replicate", "fal-ai"]
for provider in providers:
try:
client = InferenceClient(
api_key=API_TOKEN,
provider=provider
)
# Generate the image using the proper client
image = client.text_to_image(
prompt=enhanced_prompt,
negative_prompt=negative_prompt,
model="black-forest-labs/FLUX.1-Krea-dev",
width=width,
height=height,
num_inference_steps=steps,
guidance_scale=cfg_scale,
seed=seed if seed != -1 else random.randint(1, 1000000000)
)
print(f'\033[1mGeneration {key} completed with {provider}!\033[0m ({enhanced_prompt})')
return image
except Exception as provider_error:
print(f"Provider {provider} failed: {provider_error}")
if provider == providers[-1]: # Last provider
raise provider_error
continue
except Exception as e:
print(f"Error during image generation: {e}")
if "404" in str(e):
raise gr.Error("Model not found. Please ensure the FLUX.1-Krea-dev model is accessible with your API token.")
elif "503" in str(e):
raise gr.Error("The model is currently being loaded. Please try again in a moment.")
elif "401" in str(e) or "403" in str(e):
raise gr.Error("Authentication failed. Please check your HF_READ_TOKEN environment variable.")
else:
raise gr.Error(f"Image generation failed: {str(e)}")
return None
# CSS to style the app
css = """
#app-container {
max-width: 800px;
margin-left: auto;
margin-right: auto;
}
"""
# Build the Gradio UI with Blocks
with gr.Blocks(theme='Nymbo/Nymbo_Theme', css=css) as app:
# Add a title to the app
gr.HTML("<center><h1>FLUX.1-Krea-dev</h1></center>")
gr.HTML("<center><p>High-quality image generation via Model Context Protocol</p></center>")
# Container for all the UI elements
with gr.Column(elem_id="app-container"):
# Add a text input for the main prompt
with gr.Row():
with gr.Column(elem_id="prompt-container"):
with gr.Row():
text_prompt = gr.Textbox(label="Prompt", placeholder="Enter a prompt here", lines=2, elem_id="prompt-text-input")
# Accordion for advanced settings
with gr.Row():
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Textbox(label="Negative Prompt", placeholder="What should not be in the image", value="(deformed, distorted, disfigured), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, misspellings, typos", lines=3, elem_id="negative-prompt-text-input")
with gr.Row():
width = gr.Slider(label="Width", value=1024, minimum=64, maximum=1216, step=32)
height = gr.Slider(label="Height", value=1024, minimum=64, maximum=1216, step=32)
steps = gr.Slider(label="Sampling steps", value=35, minimum=1, maximum=100, step=1)
cfg = gr.Slider(label="CFG Scale", value=7, minimum=1, maximum=20, step=1)
strength = gr.Slider(label="Strength", value=0.7, minimum=0, maximum=1, step=0.001)
seed = gr.Slider(label="Seed", value=-1, minimum=-1, maximum=1000000000, step=1) # Setting the seed to -1 will make it random
method = gr.Radio(label="Sampling method", value="DPM++ 2M Karras", choices=["DPM++ 2M Karras", "DPM++ SDE Karras", "Euler", "Euler a", "Heun", "DDIM"])
# Add a button to trigger the image generation
with gr.Row():
text_button = gr.Button("Run", variant='primary', elem_id="gen-button")
# Image output area to display the generated image
with gr.Row():
# Output component only; no input image is required by the tool
image_output = gr.Image(label="Image Output", elem_id="gallery")
# Bind the button to the flux_krea_generate function for the UI only
# Hide this event as an MCP tool to avoid schema confusion (UI wires image output)
text_button.click(
flux_krea_generate,
inputs=[text_prompt, negative_prompt, steps, cfg, method, seed, strength, width, height],
outputs=image_output,
show_api=False,
api_description=False,
)
# Expose a dedicated MCP/API endpoint with a clear schema (text-to-image only)
# This avoids clients misinterpreting the UI event as requiring an input image.
gr.api(
flux_krea_generate,
api_name="generate_image",
api_description=(
"Generate an image from a text prompt using FLUX.1-Krea-dev. "
"Inputs are text and numeric parameters only; no input image is required."
),
)
# Launch the Gradio app with MCP server enabled
app.launch(show_api=True, share=False, mcp_server=True)