Skip to main content
Open or close navigation menu

Sora | GPT Image

Generate and edit images and videos from text, photos, and voice descriptions

icon of Sora | GPT Image
monthly users
Views
88
Last updated date

Sora | GPT Image is a visual content bot combining the GPT Image 2.5 and Sora 2.0 models. Create or edit an image from a text description using up to 16 reference photos, or generate a video from text, an uploaded photo, or a voice message with an idea. Formats are available for Reels, Shorts, TikTok, and YouTube, and finished results can be regenerated or remixed with a new photo. A channel subscription is required to use it.

Features

  • Create and edit images from text descriptions with GPT Image 2.5 — /start
  • Use up to 16 photos as references for image generation
  • Generate videos in Sora 2.0 from text, a photo, or a voice message
  • Frame formats for Reels, Shorts, TikTok, and YouTube
  • Regenerate and remix a finished result with a new photo
  • Access opens after subscribing to the channel
ArchitectArchitectAuthor

Audience

Comparison dates: Oct 21, 2026 — Nov 20, 2026 (UTC)

345

-40.3%

Loading comments...