Loading. Please wait...
Upload an image and get a prompt that describes its subject, composition, style, lighting, colors, and mood. Edit the result for Midjourney, DALL-E, or Stable Diffusion.
Max. image size: 1024 x 1024 pixels (Max file size: 1MB)
5 free generations per day.
The tool reads the image and writes down its subject, composition, style, lighting, colors, and mood in a prompt you can edit.
Upload a JPEG, PNG, or WebP and get a written description of the visual choices in the image.
Use the prompt as visual direction, then add a script, voice, captions, and music in Videotok.
Paste the prompt into a scene or image brief, then adjust it for each shot.
Upload a JPEG, PNG, or WebP and get a written description of the visual choices in the image.
Copy the result into DALL-E, Midjourney, Stable Diffusion, or another generator that accepts text prompts.
Change the subject, framing, style, or lighting instead of treating the first prompt as final.
How image analysis, file limits, and daily generations work.
The tool identifies the subject, composition, style, colors, lighting, and mood, then writes those details as an editable text prompt.
You can use the text with Midjourney, DALL-E, Stable Diffusion, Leonardo AI, or another image generator that accepts prompts.
We support JPEG, PNG, and WebP formats. AVIF is not supported. Maximum file size is 1MB and maximum dimensions are 1024x1024 pixels.
The public tool allows 5 generations per day. The counter in the form shows how many remain.