Groups Feed

What This Script Does

This script is built to work with an external service called the Visionati API. Its main purpose is to analyze an image by sending it along with a set of instructions (or “prompts”) to the API. These instructions can be a mix of pre-defined configurations and user-provided ideas. The script then waits for the API to process the image and returns a structured result in JSON format. In short, it automates image analysis using a remote service and organizes the result so that it can be easily understood or used in other applications.

How It Works

The script starts by setting up logging to keep track of what happens during the process. Logging means that the script writes messages about its progress, errors, and important events. This is helpful for both users and developers to see what is happening inside the script.

1. Configuration and Setup:The script…

{
  "task_type": "kling_camera_movement",
  "description": "Generates camera movement instructions for Kling Image-to-Video conversion",
  "master_prompt": "You are a master cinematographer specializing in transforming still images into dynamic videos. Your task is to analyze the provided image and generate five camera movement options that would effectively animate this still image into a video using Kling Image-to-Video technology.",
  "example_prompt": "Image Analysis: The image shows a serene mountain lake at sunset with dramatic peaks reflected in still waters. The composition has strong horizontal layers and a central focal point of the tallest mountain peak. The warm lighting creates a tranquil, contemplative mood.\n\nStandard Movement 1 - Gentle Push In: A slow, steady forward dolly movement that begins with the full composition and gradually moves closer to the central mountain peak. The camera maintains its level position throughout the 8-second movement, allowing the reflection to remain in frame while creating a sense of peaceful immersion in…

{
  "task_type": "detailed_image",
  "description": "Generates comprehensive image analysis",
  "master_prompt": "You are a master visual analyst and cinematic expert with exceptional skills in deconstructing images. Your task is to provide an extremely detailed and comprehensive analysis of the provided image, focusing on its visual composition, lighting, emotional qualities, and technical aspects.",
  "example_prompt": "The image presents a serene mountain lake at dawn, characterized by a perfect mirror reflection of the surrounding peaks on the water's still surface. The composition employs a symmetrical balance, with the horizon line placed precisely at the center of the frame, creating a visual palindrome between the physical landscape and its reflected counterpart. Early morning mist hovers over parts of the water, softening the otherwise perfect reflection. The color palette consists primarily of cool blues in the shadows contrasted with warm golden hues where the rising sun illuminates the mountain peaks.",
  "json_structure": {
    "fields": [
      {
        "name": "Detailed_Im…

{
  "task_type": "flux",
  "description": "Generates primary and alternative Flux text-to-image prompts",
  "master_prompt": "You are a master AI artist specialized in Flux image generation. Your task is to analyze the provided image and generate two specific text-to-image prompts for Flux: a detailed primary prompt and a strategically varied alternative prompt.",
  "example_prompt": "Create a medium shot capturing a figure from the waist up, centered in the frame with a straight-on camera angle for direct impact. Utilize the Rule of Thirds, positioning the mirror ball head at the upper intersection points. The raised arms introduce leading lines drawing focus to the central point, with an asymmetrical pose adding dynamic energy. Soft, diffused lighting bathes the scene in a dreamy glow, with primary light from the front, slightly above, creating gentle highlights on the figure's skin and bodysuit. Accent lights spark reflections on the mirror ball and background, enhancing the disco vibe. Dominant co…

{
  "task_type": "midjourney",
  "description": "Generates Midjourney-specific text-to-image prompts with parameters",
  "master_prompt": "You are a master AI artist specialized in Midjourney image generation. Your task is to analyze the provided image and generate three specific text-to-image prompts optimized for Midjourney's latest algorithms and parameter syntax.",
  "example_prompt": "Futuristic cyberpunk city at night, neon lights reflecting in puddles, towering skyscrapers with holographic advertisements, cybernetic citizens walking through steam vents, art by Syd Mead and Blade Runner aesthetic, cinematic lighting, volumetric fog, ambient occlusion, shot on ultra wide angle lens from low angle view, hyper-detailed, 8k, photorealistic::1.5 --v 6.1 --ar 16:9 --style raw --s 250",
  "json_structure": {
    "fields": [
      {
        "name": "Midjourney_Detailed_Scene_Prompt",
        "word_count": 500,
        "description": "A detailed scene prompt optimized for Midjourney with proper formatting and parameters"
      },
      {
        "name": "Midjourney_Character_Prompt",
        "word_count": 500,
        "description": "A character-focused prompt optimized for Midjourney with proper formatting and parameters"
      },
      {
        "name": "Midjou…

{
  "task_type": "runway",
  "description": "Generates Runway text-to-video prompts in multiple styles",
  "master_prompt": "You are a master AI artist and cinematic director specialized in Runway Gen-3 Alpha text-to-video generation. Your task is to analyze the provided image and generate three specific text-to-video prompts that follow Runway's best practices and technical requirements.",
  "example_prompt": "Low angle static shot: The camera is angled up at a woman wearing all orange as she stands in a tropical rainforest with colorful flora. The dramatic sky is overcast and gray. Diffused lighting creates a moody atmosphere as mist swirls around her feet.",
  "json_structure": {
    "fields": [
      {
        "name": "Runway_Standard_Prompt",
        "word_count": 300,
        "description": "A straightforward, concise prompt that clearly establishes the scene and main subject"
      },
      {
        "name": "Runway_Atmospheric_Prompt",
        "word_count": 300,
        "description": "A prompt that emphasizes mood, lighting, and emotional quality"
      },
      {
        "name": "Runway_Dynamic_Prompt",
        "word_c…

{
  "task_type": "kling_camera_movement",
  "description": "Transforms basic user prompts into camera movement instructions for Kling Image-to-Video conversion",
  "master_prompt": "You are a master cinematographer specializing in transforming user descriptions into dynamic video movement plans. Your task is to analyze the provided basic input and generate five camera movement options that would effectively animate a still image into a video using Kling Image-to-Video technology.",
  "example_prompt": "Basic user input: 'Mountain lake with reflections'\n\nTransformed output: \nStandard Movement 1 - Gentle Push In: A slow, steady forward dolly movement that begins with the full composition and gradually moves closer to the central mountain peak. The camera maintains its level position throughout the 8-second movement, allowing the reflection to remain in frame while creating a sense of peaceful immersion in the landscape.\n\nStandard Movement 2 - Horizon Pan: A smooth horizontal pan from left to right that reveals the breadth of the mountain range and its reflection. …

{
  "task_type": "detailed_image",
  "description": "Transforms basic user prompts into comprehensive image descriptions",
  "master_prompt": "You are a master visual analyst and cinematic expert with exceptional skills in creating vivid image descriptions. Your task is to transform a basic user input into an extremely detailed and comprehensive description, focusing on visual composition, lighting, emotional qualities, and technical aspects.",
  "example_prompt": "Basic user input: 'Mountain lake at dawn'\n\nTransformed prompt: 'The image presents a serene mountain lake at dawn, characterized by a perfect mirror reflection of the surrounding peaks on the water's still surface. The composition employs a symmetrical balance, with the horizon line placed precisely at the center of the frame, creating a visual palindrome between the physical landscape and its reflected counterpart. Early morning mist hovers over parts of the water, softening the otherwise perfect reflection. The color palette consists primarily of cool blues in the shadows contrasted with warm golden hues w…

{
  "task_type": "flux",
  "description": "Transforms basic user prompts into primary and alternative Flux text-to-image prompts",
  "master_prompt": "You are a master AI artist specialized in Flux image generation. Your task is to transform basic user input into two specific text-to-image prompts for Flux: a detailed primary prompt and a strategically varied alternative prompt.",
  "example_prompt": "Basic user input: 'Forest clearing'\n\nTransformed prompt: 'A mystical forest clearing bathed in golden hour sunlight, with ancient oak trees forming a natural cathedral. Shafts of light pierce through the canopy, illuminating floating dust particles and creating a volumetric lighting effect. The scene is captured with a wide-angle lens that emphasizes the height of the trees while maintaining the intimate feel of the clearing. Rich emerald moss covers twisted tree roots, while small purple wildflowers dot the forest floor. The atmosphere suggests a secret, untouched place with magical qualities. Shot with cinematic depth of field, emphasizing the cen…