Video Visualizer from Text - Confirm & Copy Final Agent Code

Describe

Describe your task

Refine

Refine the plan

SubAgents

Review all agents

Deploy

Deploy your agent

Review Final Agent Copy

Expand

[
  {
    "taskID": 190,
    "semanticTitleOfTask": "Generate Three Distinct Visually Rich Image Prompts from Source Text",
    "taskDescription": "This task uses a language model to analyze an original text input and produce three separate, imaginative image prompts. Each prompt should be specific, visually descriptive, and capture unique interpretations of the text, suitable for AI image generation.",
    "inputDescription": "This task requires two inputs: the original text (variable1), plus a short instruction (variable2) indicating the generation of three distinct image prompts. The language model will read the source text and create prompts that each focus on unique, renderable visual scenes.",
    "inputRequired": [
      "variable1",
      "variable2"
    ],
    "outputDescription": "A single text output containing three distinct image-generation prompts, each labeled 1), 2), and 3). These prompts include sufficient visual details such as style, mood, composition, and lighting, ensuring they clearly represent different creative takes on the original text.",
    "outputName": "three_image_prompts",
    "promptInstruction": "You are a creative visual prompt generator. Your task is to analyze the provided text and produce three distinct, detailed image prompts that capture its essence in unique ways. Each prompt must be 30–50 words, specifying scene, style, mood, and composition. Ensure each prompt is distinct and avoid placing any text within the image. Label them as 1), 2), 3)."
  },
  {
    "taskID": 222,
    "semanticTitleOfTask": "Generate PNG Image #1 from the first text prompt",
    "taskDescription": "This task uses skill #222 to generate a single PNG image from the first text prompt in the three_image_prompts array. The output is the URL of the generated image, labeled as image1.",
    "inputDescription": "Requires the first text prompt from three_image_prompts, providing a brief descriptive request for the image to be created.",
    "inputRequired": [
      "three_image_prompts"
    ],
    "outputDescription": "A PNG image URL that corresponds to the first text prompt.",
    "outputName": "image1",
    "promptInstruction": ""
  },
  {
    "taskID": 222,
    "semanticTitleOfTask": "Generate PNG Image #2 from the second text prompt",
    "taskDescription": "This task uses skill #222 to generate a single PNG image from the second text prompt in the three_image_prompts array. The output is the URL of the generated image, labeled as image2.",
    "inputDescription": "Requires the second text prompt from three_image_prompts, describing a different image to create.",
    "inputRequired": [
      "three_image_prompts"
    ],
    "outputDescription": "A PNG image URL that corresponds to the second text prompt.",
    "outputName": "image2",
    "promptInstruction": ""
  },
  {
    "taskID": 222,
    "semanticTitleOfTask": "Generate PNG Image #3 from the third text prompt",
    "taskDescription": "This task uses skill #222 to generate a single PNG image from the third text prompt in the three_image_prompts array. The output is the URL of the generated image, labeled as image3.",
    "inputDescription": "Requires the third text prompt from three_image_prompts, offering yet another distinct request for the image to be generated.",
    "inputRequired": [
      "three_image_prompts"
    ],
    "outputDescription": "A PNG image URL that corresponds to the third text prompt.",
    "outputName": "image3",
    "promptInstruction": ""
  },
  {
    "taskID": 223,
    "semanticTitleOfTask": "Format the three PNG URLs into a structured list",
    "taskDescription": "This task uses skill #223 to take the three generated PNG URLs (image1, image2, image3) and assemble them into a clean, ordered list of raw URLs. The output is labeled as three_generated_images.",
    "inputDescription": "Requires image1, image2, and image3 from the preceding tasks, which are PNG URLs to be formatted into a simple list, one URL per line.",
    "inputRequired": [
      "image1",
      "image2",
      "image3"
    ],
    "outputDescription": "A concise text output showing the three PNG URLs in their original order, one per line.",
    "outputName": "three_generated_images",
    "promptInstruction": "I am organizing three image URLs into a structured response. Please format these three URLs each on its own line, in their original order, without any commentary or additional text."
  },
  {
    "taskID": 169,
    "semanticTitleOfTask": "Create 5-Second Animated Video From Text Prompt (First Prompt)",
    "taskDescription": "This task calls the skill #169 to transform the first text prompt in the array into a short 5-second MP4 video. The resulting animation aims to visually represent the content described in that prompt.",
    "inputDescription": "Requires the text output (three_image_prompts) along with the corresponding image URL (three_generated_images) if needed. The primary input for generation is the text prompt.",
    "inputRequired": [
      "three_image_prompts",
      "three_generated_images"
    ],
    "outputDescription": "Delivers one MP4 video URL (video1) corresponding to the first animated sequence.",
    "outputName": "video1",
    "promptInstruction": "Create a 5-second animated video that captures the essence of the following text prompt. The animation should be fluid and cinematic, maintaining high visual quality throughout. Use a 16:9 aspect ratio and ensure the animation flows smoothly for the full duration. The scene should evolve naturally while staying true to the core elements of the prompt. Focus on creating a visually engaging sequence that effectively communicates the prompt's intended message."
  },
  {
    "taskID": 169,
    "semanticTitleOfTask": "Create 5-Second Animated Video From Text Prompt (Second Prompt)",
    "taskDescription": "This task calls the skill #169 to transform the second text prompt in the array into a short 5-second MP4 video. The resulting animation aims to visually represent the content described in that prompt.",
    "inputDescription": "Requires the text output (three_image_prompts) along with the corresponding image URL (three_generated_images) if needed. The primary input for generation is the text prompt.",
    "inputRequired": [
      "three_image_prompts",
      "three_generated_images"
    ],
    "outputDescription": "Delivers one MP4 video URL (video2) corresponding to the second animated sequence.",
    "outputName": "video2",
    "promptInstruction": "Create a 5-second animated video that captures the essence of the following text prompt. The animation should be fluid and cinematic, maintaining high visual quality throughout. Use a 16:9 aspect ratio and ensure the animation flows smoothly for the full duration. The scene should evolve naturally while staying true to the core elements of the prompt. Focus on creating a visually engaging sequence that effectively communicates the prompt's intended message."
  },
  {
    "taskID": 169,
    "semanticTitleOfTask": "Create 5-Second Animated Video From Text Prompt (Third Prompt)",
    "taskDescription": "This task calls the skill #169 to transform the third text prompt in the array into a short 5-second MP4 video. The resulting animation aims to visually represent the content described in that prompt.",
    "inputDescription": "Requires the text output (three_image_prompts) along with the corresponding image URL (three_generated_images) if needed. The primary input for generation is the text prompt.",
    "inputRequired": [
      "three_image_prompts",
      "three_generated_images"
    ],
    "outputDescription": "Delivers one MP4 video URL (video3) corresponding to the third animated sequence.",
    "outputName": "video3",
    "promptInstruction": "Create a 5-second animated video that captures the essence of the following text prompt. The animation should be fluid and cinematic, maintaining high visual quality throughout. Use a 16:9 aspect ratio and ensure the animation flows smoothly for the full duration. The scene should evolve naturally while staying true to the core elements of the prompt. Focus on creating a visually engaging sequence that effectively communicates the prompt's intended message."
  },
  {
    "taskID": 223,
    "semanticTitleOfTask": "Format Video URLs Into Structured List",
    "taskDescription": "This task calls skill #223 to combine the three generated MP4 URLs into a single, ordered list for neat final output.",
    "inputDescription": "Requires the three MP4 URLs returned by tasks 1, 2, and 3: video1, video2, and video3.",
    "inputRequired": [
      "video1",
      "video2",
      "video3"
    ],
    "outputDescription": "Returns one formatted list of the three MP4 URLs in plain text, numbered 1 to 3.",
    "outputName": "three_animated_videos",
    "promptInstruction": "Take the following three MP4 video URLs and format them into a clean, organized list. Each URL should appear on its own line, numbered 1., 2., 3.. Do not add any additional commentary or formatting - simply return the three URLs in order, each prefixed with its number. Maintain the exact order in which the URLs were provided."
  },
  {
    "taskID": 191,
    "semanticTitleOfTask": "JSON Assembly and Formatting of Multi-Modal Content",
    "taskDescription": "This task uses the LLM to assemble a JSON object from three sets of data: 3 prompts, 3 image URLs, and 3 video URLs. The final output is a JSON structure with an array containing three objects, each containing a prompt, image, and video property.",
    "inputDescription": "Requires three sets of inputs: three_image_prompts, three_generated_images, and three_animated_videos. Each set should contain exactly three corresponding elements that line up by index (first prompt maps to first image and first video, etc.).",
    "inputRequired": [
      "three_image_prompts",
      "three_generated_images",
      "three_animated_videos"
    ],
    "outputDescription": "Outputs a valid JSON object in the token video_urls_json, containing a 'results' array of three objects. Each object has 'prompt', 'image', and 'video' keys, mapping the provided prompts, image URLs, and video URLs by their respective index.",
    "outputName": "video_urls_json",
    "promptInstruction": "You are a JSON formatting specialist. Your task is to create a properly formatted JSON object from three sets of related content. You will receive three prompts, three image URLs, and three video URLs. Create a JSON object with a 'results' array containing three objects. Each object should have three properties: 'prompt', 'image', and 'video'. Map the first prompt with the first image URL and first video URL in the first object, and so on for all three sets. Ensure the JSON syntax is valid and properly nested. Return only the JSON object with no additional commentary or explanation."
  }
]

Happy? Now Copy-Paste To Proceed...

BACK TO SUBAGENTS

COPY TO CLIPBOARD