ToolCabana

Product shadow maker

Add a soft synthetic shadow beneath a cutout.

Favorites are saved in this browser. Find them in My favorites.

Product shadow maker

Your input stays in this browser unless stated otherwise
Clear your input, files and result, and restore the default settings.

Drop your files here

or choose files from your device

كيفية استخدام Product shadow maker

  1. Choose a source file. If the tool accepts multiple files, arrange them in the order you want.
  2. Set background color, shadow opacity percent.
  3. Run product shadow maker, review the output, then use the available copy or download controls.

وظائف هذه الأداة

Downloads a browser inference model on first run, then processes source locally in a cancellable Web Worker. Background removal uses BEN2; transcription uses Whisper tiny. Review recognition errors and image edges.

Background color
Set this value for your task.
Shadow opacity percent
Range: 0 to 100

الحدود والمعالجة

Image inputs: up to 32 megapixels, batches up to 10 images. Audio/video uploads: 50 MB; transcription: 120 seconds. Edited videos: 20 seconds, 4 fps and 640 pixels wide. Translation: English/Spanish, 30,000 characters; subtitles: 200 cues. Neural speech: 1,000 English characters. Model downloads and memory requirements vary by device.

مثال للإدخال
A useful tool makes everyday work easier. Review the results before sharing.

الأسئلة الشائعة

What does product shadow maker do?

Downloads a browser inference model on first run, then processes source locally in a cancellable Web Worker. Background removal uses BEN2; transcription uses Whisper tiny. Review recognition errors and image edges.

Where is my input processed?

Source files and text stay in this browser. The first run downloads public models from Hugging Face and local runtime assets from the site. Models may remain in the browser cache. No source upload to Vercel, Supabase or a conversion service is required.

What are the input limits?

Image inputs: up to 32 megapixels, batches up to 10 images. Audio/video uploads: 50 MB; transcription: 120 seconds. Edited videos: 20 seconds, 4 fps and 640 pixels wide. Translation: English/Spanish, 30,000 characters; subtitles: 200 cues. Neural speech: 1,000 English characters. Model downloads and memory requirements vary by device.