artificialguybr's picture
Update app.py
abf8eed
raw
history blame
5.3 kB
import gradio as gr
import requests
import io
from PIL import Image
import json
import os
import logging
import time
from tqdm import tqdm
from image_processing import downscale_image, limit_colors, resize_image, convert_to_grayscale, convert_to_black_and_white
# Placeholder class for processed images
class SomeClass:
def __init__(self):
self.images = []
with open('loras.json', 'r') as f:
loras = json.load(f)
def update_selection(selected_state: gr.SelectData):
selected_lora_index = selected_state.index
selected_lora = loras[selected_lora_index]
new_placeholder = f"Type a prompt for {selected_lora['title']}"
lora_repo = selected_lora["repo"]
updated_text = f"### Selected: [{lora_repo}](https://huggingface.co/{lora_repo}) ✨"
return (
gr.update(placeholder=new_placeholder),
updated_text,
selected_state
)
def run_lora(prompt, selected_state, pixel_art_options, postprocess_options, progress=gr.Progress(track_tqdm=True)):
selected_lora_index = selected_state.index
selected_lora = loras[selected_lora_index]
api_url = f"https://api-inference.huggingface.co/models/{selected_lora['repo']}"
payload = {
"inputs": f"{prompt} {selected_lora['trigger_word']}",
"parameters": {"negative_prompt": "bad art, ugly, watermark, deformed"},
}
response = requests.post(api_url, json=payload)
if response.status_code == 200:
original_image = Image.open(io.BytesIO(response.content))
processed = SomeClass()
processed.images = [original_image]
pixel_art_script = PixelArtScript()
postprocess_script = ScriptPostprocessingUpscale()
pixel_art_script.postprocess(
processed,
**pixel_art_options
)
postprocess_script.process(
processed,
**postprocess_options
)
refined_image = processed.images[-1]
return original_image, refined_image
def apply_post_processing(image, image_processing_options):
processed_image = image.copy()
if image_processing_options['downscale'] > 1:
processed_image = downscale_image(processed_image, image_processing_options['downscale'])
if image_processing_options['limit_colors']:
processed_image = limit_colors(processed_image)
if image_processing_options['grayscale']:
processed_image = convert_to_grayscale(processed_image)
if image_processing_options['black_and_white']:
processed_image = convert_to_black_and_white(processed_image)
return processed_image
with gr.Blocks() as app:
title = gr.Markdown("# artificialguybr LoRA portfolio")
description = gr.Markdown("### This is a Pixel Art Generator using SD Loras.")
selected_state = gr.State()
with gr.Row():
gallery = gr.Gallery(
[(item["image"], item["title"]) for item in loras],
label="LoRA Gallery",
allow_preview=False,
columns=3
)
with gr.Column():
prompt_title = gr.Markdown("### Click on a LoRA in the gallery to create with it")
selected_info = gr.Markdown("")
with gr.Row():
prompt = gr.Textbox(label="Prompt", show_label=False, lines=1, max_lines=1, placeholder="Type a prompt after selecting a LoRA")
button = gr.Button("Run")
result = gr.Image(interactive=False, label="Generated Image")
refined_result = gr.Image(interactive=False, label="Refined Generated Image")
# New Output for Post-Processed Image
post_processed_result = gr.Image(interactive=False, label="Post-Processed Image")
# New UI elements for pixel art options
with gr.Row():
pixel_art_options = PixelArtScript().ui(True)
postprocess_options = ScriptPostprocessingUpscale().ui()
# New UI elements for image processing options
with gr.Row():
downscale = gr.Slider(minimum=1, maximum=10, step=1, label="Downscale")
limit_colors = gr.Checkbox(label="Limit Colors")
grayscale = gr.Checkbox(label="Grayscale")
black_and_white = gr.Checkbox(label="Black and White")
image_processing_options = {
'downscale': downscale,
'limit_colors': limit_colors,
'grayscale': grayscale,
'black_and_white': black_and_white
}
post_process_button = gr.Button("Apply Post-Processing")
gallery.select(
update_selection,
outputs=[prompt, selected_info, selected_state]
)
prompt.submit(
fn=run_lora,
inputs=[prompt, selected_state, pixel_art_options, postprocess_options],
outputs=[result, refined_result]
)
post_process_button.click(
fn=apply_post_processing,
inputs=[refined_result, image_processing_options],
outputs=[post_processed_result]
)
app.queue(max_size=20, concurrency_count=5)
app.launch()