import gradio as gr import requests import io import os import logging from PIL import Image from image_processing import downscale_image, limit_colors, convert_to_grayscale, convert_to_black_and_white, resize_image, DITHER_METHODS, QUANTIZATION_METHODS import json import time # Configuração de log logging.basicConfig(level=logging.DEBUG) 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): logging.debug(f"Inside update_selection, selected_state: {selected_state}") logging.debug(f"Content of selected_state: {vars(selected_state)}") # Log the content 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, progress=gr.Progress(track_tqdm=True)): logging.debug(f"Inside run_lora, selected_state: {selected_state}") logging.debug(f"Content of selected_state in run_lora: {vars(selected_state)}") if not selected_state: logging.error("selected_state is None or empty. Make sure a LoRA is selected.") raise gr.Error("You must select a LoRA before proceeding.") token = os.getenv("API_TOKEN") if not token: logging.error("API_TOKEN is not set.") raise gr.Error("API_TOKEN is not set.") selected_lora_index = selected_state.index selected_lora = loras[selected_lora_index] api_url = f"https://api-inference.huggingface.co/models/{selected_lora['repo']}" trigger_word = selected_lora["trigger_word"] payload = { "inputs": f"{prompt} {trigger_word}", "parameters": {"negative_prompt": "bad art, ugly, watermark, deformed"}, } headers = {"Authorization": f"Bearer {token}"} logging.debug(f"API Request: {api_url}") logging.debug(f"API Payload: {payload}") error_count = 0 while True: response = requests.post(api_url, json=payload, headers=headers) if response.status_code == 200: return Image.open(io.BytesIO(response.content)) elif response.status_code == 503: time.sleep(1) elif response.status_code == 500 and error_count < 5: logging.error(response.content) time.sleep(1) error_count += 1 else: logging.error(f"Unexpected API Error: {response.status_code}") raise gr.Error(f"Unexpected API Error: {response.status_code}") def postprocess( image, enabled, downscale, need_rescale, enable_color_limit, number_of_colors, quantization_method, dither_method, use_k_means, is_grayscale, number_of_shades, quantization_method_grayscale, dither_method_grayscale, use_k_means_grayscale, is_black_and_white, is_inversed_black_and_white, black_and_white_threshold, use_color_palette, palette_image, palette_colors, dither_method_palette ): if not enabled: return image processed_image = image.copy() if downscale > 1: processed_image = downscale_image(processed_image, downscale) if enable_color_limit: processed_image = limit_colors( image=processed_image, limit=number_of_colors, quantize=QUANTIZATION_METHODS[quantization_method], dither=DITHER_METHODS[dither_method], use_k_means=use_k_means ) if is_grayscale: processed_image = convert_to_grayscale(processed_image) processed_image = limit_colors( image=processed_image, limit=number_of_shades, quantize=QUANTIZATION_METHODS[quantization_method_grayscale], dither=DITHER_METHODS[dither_method_grayscale], use_k_means=use_k_means_grayscale ) if is_black_and_white: processed_image = convert_to_black_and_white(processed_image, black_and_white_threshold, is_inversed_black_and_white) if use_color_palette: processed_image = limit_colors( image=processed_image, palette=palette_image, palette_colors=palette_colors, dither=DITHER_METHODS[dither_method_palette] ) if need_rescale: processed_image = resize_image(processed_image, image.size) return processed_image def run_and_postprocess(prompt, selected_state, enabled, downscale, need_rescale, enable_color_limit, palette_size_color, quantization_methods_color, dither_methods_color, k_means_color, enable_grayscale, palette_size_gray, quantization_methods_gray, dither_methods_gray, k_means_gray, enable_black_and_white, inverse_black_and_white, threshold_black_and_white, enable_custom_palette, palette_image, palette_size_custom, dither_methods_custom): # Debug: Starting the function logging.debug("Starting run_and_postprocess function.") # Run the original image generation original_image = run_lora(prompt, selected_state) # Debug: Confirming that the original image was generated logging.debug("Original image generated.") # Post-process the image based on user input processed_image = postprocess( original_image, enabled, downscale, need_rescale, enable_color_limit, palette_size_color, quantization_methods_color, dither_methods_color, k_means_color, enable_grayscale, palette_size_gray, quantization_methods_gray, dither_methods_gray, k_means_gray, enable_black_and_white, inverse_black_and_white, threshold_black_and_white, enable_custom_palette, palette_image, palette_size_custom, dither_methods_custom ) # Debug: Confirming that post-processing was applied if enabled: logging.debug("Post-processing applied.") else: logging.debug("Post-processing not applied.") return processed_image if enabled else original_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=1) 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") # Accordion moved here, inside the same gr.Blocks context with gr.Accordion(label="Pixel art", open=True): with gr.Row(): enabled = gr.Checkbox(label="Enable", value=False) downscale = gr.Slider(label="Downscale", minimum=1, maximum=32, step=2, value=8) need_rescale = gr.Checkbox(label="Rescale to original size", value=True) with gr.Tabs(): with gr.TabItem("Color"): enable_color_limit = gr.Checkbox(label="Enable", value=False) palette_size_color = gr.Slider(label="Palette Size", minimum=1, maximum=256, step=1, value=16) quantization_methods_color = gr.Radio(choices=["Median Cut", "Maximum Coverage", "Fast Octree"], label="Colors Quantization Method", value="Median Cut") dither_methods_color = gr.Radio(choices=["None", "Floyd-Steinberg"], label="Colors Dither Method", value="None") k_means_color = gr.Checkbox(label="Enable k-means for color quantization", value=True) with gr.TabItem("Grayscale"): enable_grayscale = gr.Checkbox(label="Enable", value=False) palette_size_gray = gr.Slider(label="Palette Size", minimum=1, maximum=256, step=1, value=16) quantization_methods_gray = gr.Radio(choices=["Median Cut", "Maximum Coverage", "Fast Octree"], label="Colors Quantization Method", value="Median Cut") dither_methods_gray = gr.Radio(choices=["None", "Floyd-Steinberg"], label="Colors Dither Method", value="None") k_means_gray = gr.Checkbox(label="Enable k-means for color quantization", value=True) with gr.TabItem("Black and white"): enable_black_and_white = gr.Checkbox(label="Enable", value=False) inverse_black_and_white = gr.Checkbox(label="Inverse", value=False) threshold_black_and_white = gr.Slider(label="Threshold", minimum=1, maximum=256, step=1, value=128) with gr.TabItem("Custom color palette"): enable_custom_palette = gr.Checkbox(label="Enable", value=False) palette_image = gr.Image(label="Color palette image", type="pil") palette_size_custom = gr.Slider(label="Palette Size", minimum=1, maximum=256, step=1, value=16) dither_methods_custom = gr.Radio(choices=["None", "Floyd-Steinberg"], label="Colors Dither Method", value="None") # The rest of your code for setting up the app gallery.select(update_selection, outputs=[prompt, selected_info, selected_state]) prompt.submit(fn=run_lora, inputs=[prompt, selected_state], outputs=[result]) button.click( fn=run_and_postprocess, inputs=[ prompt, selected_state, enabled, downscale, need_rescale, enable_color_limit, palette_size_color, quantization_methods_color, dither_methods_color, k_means_color, enable_grayscale, palette_size_gray, quantization_methods_gray, dither_methods_gray, k_means_gray, enable_black_and_white, inverse_black_and_white, threshold_black_and_white, enable_custom_palette, palette_image, palette_size_custom, dither_methods_custom ], outputs=[result] ) app.queue(max_size=20, concurrency_count=5) app.launch()