ZenVidi
⬅️ Back

📖 Video Generation Guide

🎬 Text to Video — Create video from text

This mode lets you create a video just by describing a scene in text — no photos needed.

Step 1. Go to the generation page and select Text to Video

Step 2. Enter a detailed description of the scene in English. For example: «A young woman driving a red sports car along a coastal road at sunset, cinematic style»

Step 3. Choose duration (4, 6 or 8 seconds) and video format

Step 4. Click Create and wait 1-2 minutes

🖼️ Image to Video — Bring your photo to life

This mode lets you upload any image and turn it into a video using ChatGPT.

Step 1. Upload your photo to ChatGPT and write a prompt, for example: «Generate a realistic photo of this person driving a sports car»

Step 2. Save the generated image from ChatGPT

Step 3. Go to the generation page, select Image to Video and upload the saved image

Step 4. Enter a description of the motion or scene in English, for example: «Driving fast along the coast, wind in hair, cinematic»

Step 5. Click Create and wait for the result

⚠️ Content Rules

• Describe scenes without mentioning violence, weapons, or explicit content

• Avoid words: stunning, sexy, naked, violence and similar

• If generation failed — rephrase the prompt and try again

• Credits are returned automatically if blocked