🎬 Ultimate AI Video Prompt Generator. From Raw Idea to Cinematic Perfection

Task: Transform the given input into a highly detailed, optimized, and structured positive prompt **and** a corresponding negative prompt for AI video generation.

Output Language: Only English

**1. Positive Prompt Structure:**

- Core Description:
    - Scene: Detailed environment, setting.
    - Subject: Who or what is the main focus? Appearance?
    - Action & Movement: What is the subject doing? How are objects or environment moving? Describe the specific motion and pacing.
    - Expressions & Emotions: Facial expressions, body language, emotional tone.
- Camera & Framing: Describe camera movement (pan, tilt, zoom, dolly), angle, shot type (close-up, wide shot), dynamic composition.
- Lighting: Type, source, direction, how it changes over time.
- Mood & Atmosphere: Overall feeling, ambiance.
- Duration: (Optional but helpful) Target length of the video clip (e.g., 4 seconds, 8 seconds).

- Artistic Style & Medium: Realistic, photorealistic, cinematic, 3D render, digital painting, anime, stop-motion, etc. Specify the visual aesthetic.

- Technical Enhancements:
    - Ultra-high definition (UHD) or 4K resolution.
    - Smooth and fluid motion.
    - Professional cinematography.
    - Rich depth of field.
    - Detailed color grading.
    - Intricate textures and materials.
    - Visual effects (if any, e.g., subtle dust particles, lens flares).

**2. Negative Prompt Structure:**

- Purpose: To specify elements, styles, qualities, and artifacts to *avoid* in the generated video.
- Content: Generate a list of terms relevant to avoiding common AI generation issues and undesirable outcomes. Standard inclusions should cover:
    - Low Quality: blurry, pixelated, low resolution, noisy, grainy, jpeg artifacts.
    - Deformities: deformed, mutated, distorted bodies, unrealistic anatomy, extra limbs, fused fingers, malformed hands, disfigured faces.
    - Unwanted Elements: text, words, letters, writing, watermark, signature, UI elements, overlay.
    - Undesired Styles (unless requested): drawing, sketch, illustration, cartoon, anime (if targeting photorealism), painting.
    - Poor Execution: bad composition, cropped, poorly framed, jerky motion, flickering, stuttering, glitches, artifacts.
    - Specific Exclusions: Add any elements explicitly implied to be avoided by the positive prompt's goal.

**Input Handling:**

- Input: [Insert a simple description, raw idea, or attach a reference file (e.g., “a cyberpunk street at night with rain”, image, or video)]
- If File Provided:
    - If Image: Analyze the image's subject, scene, style, and composition. Describe how it transitions into a dynamic video clip, specifying initial state and subsequent action/camera movement for the positive prompt. Generate a standard negative prompt, adding exclusions if implied by the image style.
    - If Video: Conduct a precise analysis of the video's content, action, camera work, editing pace, and visual style. Generate a positive prompt that recreates it accurately. Generate a negative prompt focused on avoiding common video generation flaws and deviations from the source style.

**Key Optimization Rules (Apply to Positive Prompt):**