{ "id": "e8172110-ec08-421b-a6f5-842e6451911f", "snapshot": "gimp", "instruction": "Open 'character.png' in GIMP and extract the pixel art character. Save the selected character as 'character_gimp.png'. Additionally, write a Python script to automate this selection process, ensuring it precisely mimics the manual extraction done in GIMP. Output the result from the script as 'character_code.png'.", "source": "", "config": [ { "type": "download", "parameters": { "files": [ { "url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/e8172110-ec08-421b-a6f5-842e6451911f/character.png", "path": "/home/user/Desktop/character.png" } ] } }, { "type": "execute", "parameters": { "command": [ "python3", "-c", "with open('/home/user/Desktop/test.py', 'w', encoding='utf-8') as f: f.write('''from PIL import Image, ImageDraw\\nimport numpy as np\\nimport sys\\nimport os\\n\\ndef extract_character_gimp_style(image_path, output_path, bg_threshold=10):\\n \\\"\\\"\\\"\\n 模仿GIMP手动提取过程，精确扣除背景并提取角色\\n \\n 参数:\\n image_path: 输入图像路径\\n output_path: 输出图像路径\\n bg_threshold: 背景检测阈值（0-255），值越小越严格\\n \\\"\\\"\\\"\\n \\n # 打开图像\\n try:\\n img = Image.open(image_path)\\n except FileNotFoundError:\\n print(f\\\"错误：找不到文件 {image_path}\\\")\\n return False\\n except Exception as e:\\n print(f\\\"错误：无法打开图像 - {e}\\\")\\n return False\\n \\n print(f\\\"已加载图像: {image_path}\\\")\\n print(f\\\"图像尺寸: {img.size}\\\")\\n print(f\\\"图像模式: {img.mode}\\\")\\n \\n # 转换为RGBA模式（如果需要）\\n if img.mode != \\'RGBA\\':\\n img = img.convert(\\'RGBA\\')\\n \\n # 获取图像数据\\n data = np.array(img)\\n \\n # 找到最可能为背景的颜色（通常是图像边缘的颜色）\\n # 获取图像四角的像素作为背景样本\\n height, width, _ = data.shape\\n corners = [\\n data[0, 0], # 左上角\\n data[0, width-1], # 右上角\\n data[height-1, 0], # 左下角\\n data[height-1, width-1] # 右下角\\n ]\\n \\n # 计算背景颜色的平均值\\n bg_color = np.mean(corners, axis=0).astype(int)\\n print(f\\\"检测到的背景颜色 (RGBA): {bg_color}\\\")\\n \\n # 方法1: 使用魔棒工具类似的方法（基于颜色相似度）\\n # 创建透明背景的新图像\\n new_data = data.copy()\\n \\n # 计算每个像素与背景颜色的差异\\n color_diff = np.sqrt(np.sum((data[:, :, :3] - bg_color[:3]) ** 2, axis=2))\\n \\n # 应用阈值来识别背景像素\\n # 对于像素艺术，通常需要较严格的阈值\\n bg_mask = color_diff <= bg_threshold\\n \\n # 将背景像素设置为完全透明\\n new_data[bg_mask, 3] = 0 # 设置alpha通道为0（透明）\\n \\n # 方法2: 边缘检测增强（可选，用于更精确的边缘）\\n # 对于像素艺术，我们可能想要保留锐利的边缘\\n for i in range(1, height-1):\\n for j in range(1, width-1):\\n # 如果当前像素不是背景，但周围有背景像素，确保它保持不透明\\n if not bg_mask[i, j] and (bg_mask[i-1, j] or bg_mask[i+1, j] or \\n bg_mask[i, j-1] or bg_mask[i, j+1]):\\n # 确保边缘像素保持不透明\\n new_data[i, j, 3] = 255\\n \\n # 创建输出图像\\n result_img = Image.fromarray(new_data, \\'RGBA\\')\\n \\n # 可选：添加一个棋盘背景用于预览（模仿GIMP的透明背景显示）\\n preview_img = create_checkerboard_background(result_img)\\n \\n # 保存结果\\n result_img.save(output_path, \\'PNG\\')\\n print(f\\\"已保存提取的角色到: {output_path}\\\")\\n \\n # 保存预览版本（带棋盘背景）\\n preview_path = output_path.replace(\\'.png\\', \\'_preview.png\\')\\n preview_img.save(preview_path, \\'PNG\\')\\n print(f\\\"已保存预览图像到: {preview_path}\\\")\\n \\n return True\\n\\ndef create_checkerboard_background(image, tile_size=10):\\n \\\"\\\"\\\"\\n 创建棋盘背景（模仿GIMP的透明背景显示）\\n \\\"\\\"\\\"\\n # 创建棋盘背景\\n checkerboard = Image.new(\\'RGB\\', image.size, (255, 255, 255))\\n draw = ImageDraw.Draw(checkerboard)\\n \\n # 绘制棋盘格子\\n for x in range(0, image.width, tile_size * 2):\\n for y in range(0, image.height, tile_size * 2):\\n # 绘制灰色格子\\n draw.rectangle([x, y, x + tile_size, y + tile_size], fill=(200, 200, 200))\\n draw.rectangle([x + tile_size, y + tile_size, \\n x + tile_size * 2, y + tile_size * 2], fill=(200, 200, 200))\\n \\n # 将角色合成到棋盘背景上\\n if image.mode == \\'RGBA\\':\\n checkerboard.paste(image, (0, 0), image)\\n else:\\n checkerboard.paste(image, (0, 0))\\n \\n return checkerboard\\n\\ndef manual_background_selection(image_path, output_path):\\n \\\"\\\"\\\"\\n 手动选择背景颜色（更精确的方法）\\n 对于特殊情况，可以手动指定背景颜色\\n \\\"\\\"\\\"\\n img = Image.open(image_path).convert(\\'RGBA\\')\\n data = np.array(img)\\n \\n # 显示图像并让用户选择背景颜色\\n print(\\\"\\\\n手动背景选择模式:\\\")\\n print(\\\"1. 请查看图像并确定背景颜色\\\")\\n print(\\\"2. 输入背景颜色的RGBA值（如：255 255 255 255）\\\")\\n \\n try:\\n bg_input = input(\\\"输入背景颜色 (R G B A)，或按Enter使用自动检测: \\\").strip()\\n if bg_input:\\n bg_color = list(map(int, bg_input.split()))\\n if len(bg_color) < 3:\\n print(\\\"错误：需要至少3个颜色值（RGB）\\\")\\n return False\\n if len(bg_color) == 3:\\n bg_color.append(255) # 默认不透明\\n else:\\n # 使用自动检测的背景颜色\\n return extract_character_gimp_style(image_path, output_path)\\n except ValueError:\\n print(\\\"错误：请输入有效的数字\\\")\\n return False\\n \\n # 创建新图像数据\\n new_data = data.copy()\\n \\n # 精确匹配背景颜色\\n tolerance = 20 # 容差\\n bg_color = np.array(bg_color[:4])\\n \\n # 计算颜色差异\\n diff = np.sqrt(np.sum((data[:, :, :4] - bg_color) ** 2, axis=2))\\n \\n # 应用容差阈值\\n bg_mask = diff <= tolerance\\n \\n # 将背景设为透明\\n new_data[bg_mask, 3] = 0\\n \\n # 保存结果\\n result_img = Image.fromarray(new_data, \\'RGBA\\')\\n result_img.save(output_path, \\'PNG\\')\\n \\n # 创建预览\\n preview_img = create_checkerboard_background(result_img)\\n preview_path = output_path.replace(\\'.png\\', \\'_preview.png\\')\\n preview_img.save(preview_path, \\'PNG\\')\\n \\n print(f\\\"已保存手动提取的结果到: {output_path}\\\")\\n print(f\\\"已保存预览图像到: {preview_path}\\\")\\n \\n return True\\n\\ndef main():\\n \\\"\\\"\\\"主函数\\\"\\\"\\\"\\n input_file = \\\"character.png\\\"\\n output_file = \\\"character_code.png\\\"\\n \\n # 检查输入文件是否存在\\n if not os.path.exists(input_file):\\n print(f\\\"错误：输入文件 \\'{input_file}\\' 不存在\\\")\\n print(\\\"请确保 \\'character.png\\' 在当前目录中\\\")\\n return\\n \\n print(\\\"=== 像素艺术角色提取工具 ===\\\")\\n print(f\\\"输入文件: {input_file}\\\")\\n print(f\\\"输出文件: {output_file}\\\")\\n print(\\\"\\\\n选择提取模式:\\\")\\n print(\\\"1. 自动提取（推荐）\\\")\\n print(\\\"2. 手动选择背景颜色\\\")\\n \\n try:\\n choice = input(\\\"请输入选择 (1 或 2，默认1): \\\").strip()\\n except KeyboardInterrupt:\\n print(\\\"\\\\n操作取消\\\")\\n return\\n \\n if choice == \\\"2\\\":\\n success = manual_background_selection(input_file, output_file)\\n else:\\n # 尝试不同的阈值以获得最佳结果\\n for threshold in [5, 10, 15, 20]:\\n print(f\\\"\\\\n尝试阈值 {threshold}...\\\")\\n temp_output = f\\\"character_threshold_{threshold}.png\\\"\\n success = extract_character_gimp_style(input_file, temp_output, threshold)\\n if success:\\n print(f\\\"阈值 {threshold} 处理完成\\\")\\n \\n # 使用默认阈值10作为最终结果\\n success = extract_character_gimp_style(input_file, output_file, bg_threshold=10)\\n \\n if success:\\n print(\\\"\\\\n\\\" + \\\"=\\\"*50)\\n print(\\\"提取完成！\\\")\\n print(f\\\"主要结果: {output_file}\\\")\\n print(f\\\"预览版本: character_code_preview.png\\\")\\n print(\\\"其他阈值测试结果已保存为 character_threshold_*.png\\\")\\n print(\\\"=\\\"*50)\\n else:\\n print(\\\"提取失败，请检查输入图像和参数。\\\")\\n\\nif __name__ == \\\"__main__\\\":\\n main()\\n''')" ], "shell": false } }, { "type": "launch", "parameters": { "command": [ "gimp", "/home/user/Desktop/character.png" ] } } ], "trajectory": "trajectories/", "related_apps": [ "gimp", "vs_code" ], "evaluator": { "func": [ "check_structure_sim_with_threshold", "check_structure_sim_with_threshold" ], "result": [ { "type": "vm_file", "path": "/home/user/Desktop/character_gimp.png", "dest": "character_gimp.png" }, { "type": "vm_file", "path": "/home/user/Desktop/character_code.png", "dest": "character_code.png" } ], "expected": [ { "type": "cloud_file", "path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/e8172110-ec08-421b-a6f5-842e6451911f/character_no_background_gold.png", "dest": "character_no_background_gold.png" }, { "type": "cloud_file", "path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/e8172110-ec08-421b-a6f5-842e6451911f/character_no_background_gold.png", "dest": "character_no_background_gold.png" } ], "options": [ { "ssim_threshold": 0.85 }, { "ssim_threshold": 0.85 } ] }, "proxy": false, "fixed_ip": false, "possibility_of_env_change": "low" }