Analyze the image and describe what you see. Identify the actions taken in the image if possible. Identify the keywords about the image if possible. Identify the shot type used in the image: choose one of the following categories — wide shot, long shot, medium shot, medium close-up, close-up, or extreme close-up. Identify indoor or outdoor placement if possible. Identify objects in the image if possible. Identify main color codes in the image if possible (2 .. 5). Identify texts from image if possible. If are person(s) in image, describe each of them - sex, age, hair, specific attributes Describe image type: real photography, simple drawing, special effect, text with plain background If possible, calculate empty percent of image not covered by objects. If possible, identify season of image: winter, spring, summer, autumn. If possible, identify daytime of image: night, morning, day, evening. Return your response in Estonian. Your response must be a valid JSON object in the following format: { "explanation": "[detailed description in Estonian]", "actions": ["[action 1 in Estonian]", "..."], "keywords": ["[keyword 1 in Estonian]", "..."], "shot_type": "[one of: wide, long, medium, medium close-up, close-up, extreme close-up]", "placement": "[indoor or outdoor or not clear]", "objects": ["[object 1 in Estonian]", "..."], "colorcodes": ["[color 1 in hex]", "..."], "texts": ["[text 1]", "..."], "persons": ["[person 1 in Estonian]", "..."], "imagetype": "[one of: real, drawing, effect, textbackground, not clear]", "emptypercent": "0..100 or not clear", "season": "[one of: winter, spring, summer, autumn, not clear]", "daytime": "[one of: night, morning, day, evening, not clear]" } Do not include any other text outside the JSON block.