Subject and action
Identify the main subject, visible behavior, environment, wardrobe, materials, and continuity cues.
ShipAny
Upload a short clip and turn its subject, composition, camera, light, color, and style into model-ready prompts.
Sample frames locally, analyze the visual language, and generate one reusable structured video prompt.
Your analysis and one complete structured video prompt will appear here.
Reopen prompt sets generated from your videos.
Six visual dimensions are extracted from representative frames, then translated into prompts for the model you choose.
Identify the main subject, visible behavior, environment, wardrobe, materials, and continuity cues.
Describe framing, visual balance, depth layers, foreground relationships, and aspect-ratio intent.
Estimate shot size, angle, lens character, camera movement, focus behavior, and spatial perspective.
Read key direction, softness, contrast, practical sources, atmosphere, and time-of-day cues.
Capture the dominant palette, saturation, contrast, temperature, and grading character.
Translate texture, genre, production design, motion rhythm, and finishing into generation language.
The browser handles the heavy media work before the AI sees a compact set of representative frames.
Select a video up to 50 MB and 2 minutes. File size and duration are checked locally.
The browser detects visual changes and selects four to eight representative frames without uploading the original video.
Receive one reusable prompt with global setup and a complete time-based script.
Start with short clips and scale prompt generation with your workflow.
Starter
For individuals
Pro
For growing teams
Enterprise
For large organizations
What happens to your video and how the analysis works.
Bring the footage. Leave with structured visual analysis and one complete video generation prompt.