{"id":260623,"date":"2026-07-28T11:35:39","date_gmt":"2026-07-28T18:35:39","guid":{"rendered":"https:\/\/picsart.com\/blog\/?p=260623"},"modified":"2026-07-28T11:35:39","modified_gmt":"2026-07-28T18:35:39","slug":"how-to-use-gemini-omni","status":"publish","type":"post","link":"https:\/\/picsart.com\/blog\/how-to-use-gemini-omni\/","title":{"rendered":"How to use Gemini Omni to create and edit AI video by chat"},"content":{"rendered":"\r\n

Gemini Omni is Google DeepMind’s unified multimodal video model, and it does something most video models cannot: it generates a video with sound from a prompt, then lets you keep editing that video by conversation, one plain-English instruction at a time. The easiest way to use it is on Picsart, which offers it as Google Omni, with no install and no API setup: open the Picsart AI Video Generator<\/a>, select Google Omni<\/a>, describe the shot you want, and generate.<\/p>\r\n

This guide covers what Gemini Omni is, how to make your first video step by step, how to edit it by chat, how to write prompts, and what you can create. By the end, you will have a finished, sound-on clip you can refine without starting over.<\/p>\r\n

What is Gemini Omni?<\/span><\/h2>\r\n

Gemini Omni is Google’s native multimodal video model, offered on Picsart as Google Omni. “Multimodal” is the key word: it takes text, image, video, and audio as input, and it generates video with synchronized audio in a single pass. Where most models hand back a silent clip, Gemini Omni delivers the scene and its soundtrack together, including dialogue, ambient sound, and true-to-life sound effects.<\/p>\r\n

Its signature is conversational editing. After a video is generated, you refine it by chat, and the model changes only what you ask while keeping the rest of the scene stable, turn after turn. It is also a world model, with an intuitive grasp of physics like gravity and fluid dynamics, which helps motion and materials behave believably.<\/p>\r\n

On Picsart, Gemini Omni arrives across four places creators already work: the AI Playground<\/a>, the AI Video Generator<\/a>, the AI Video Editor<\/a>, and Picsart Flow<\/a>. You can also run it against other video models<\/a> on the same prompt. For the full rundown, see the Gemini Omni launch in Picsart<\/a>.<\/p>\r\n

Gemini Omni at a glance<\/span><\/h2>\r\n\r\n
\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n
Feature<\/th>\r\nDetail<\/th>\r\n<\/tr>\r\n<\/thead>\r\n
Developer<\/td>\r\nGoogle DeepMind<\/td>\r\n<\/tr>\r\n
Type<\/td>\r\nUnified multimodal video model<\/td>\r\n<\/tr>\r\n
Inputs<\/td>\r\nText, image, video, audio<\/td>\r\n<\/tr>\r\n
Editing<\/td>\r\nConversational, multi-turn; edits uploaded video<\/td>\r\n<\/tr>\r\n
Audio<\/td>\r\nSynchronized in one pass; lip-sync in 6 languages; Foley<\/td>\r\n<\/tr>\r\n
Clip length<\/td>\r\nUp to 10 seconds<\/td>\r\n<\/tr>\r\n
Aspect ratios<\/td>\r\n16:9 and 9:16<\/td>\r\n<\/tr>\r\n
Reference images<\/td>\r\nUp to 5<\/td>\r\n<\/tr>\r\n
Strengths<\/td>\r\nPhysics-aware motion, multi-shot storytelling, on-screen text<\/td>\r\n<\/tr>\r\n
Best for<\/td>\r\nEdit-after-generate, storytelling, marketing content<\/td>\r\n<\/tr>\r\n<\/tbody>\r\n<\/table>\r\n<\/figure>\r\n\r\n

How to use Gemini Omni on Picsart, step by step<\/span><\/h2>\r\n

You can make a Gemini Omni video in a few minutes, with no account juggling or setup. Here is the full flow:<\/p>\r\n

\n

How to use Gemini Omni on Picsart, step by step<\/h2>\n \n
\n
\n
\n

\n 1.<\/span>\n Open the AI Video Generator <\/p>\n

Open the Picsart AI Video Generator or AI Playground.<\/p>\n

\n \n \n \"\"\n Open the AI Video Generator<\/span>\n <\/button>\n <\/div>\n <\/div>\n <\/div>\n
\n
\n

\n 2.<\/span>\n Select Google Omni <\/p>\n

Select Google Omni as the model.<\/p>\n <\/div>\n <\/div>\n

\n
\n

\n 3.<\/span>\n Write your prompt <\/p>\n

Type a prompt describing the scene, the action, and the sound you want.<\/p>\n <\/div>\n <\/div>\n

\n
\n

\n 4.<\/span>\n Set aspect ratio and references <\/p>\n

Set the aspect ratio, and add a photo or reference image if you want to guide the result.<\/p>\n <\/div>\n <\/div>\n

\n
\n

\n 5.<\/span>\n Generate with audio <\/p>\n

Generate the video, with audio, in one pass.<\/p>\n <\/div>\n <\/div>\n

\n
\n

\n 6.<\/span>\n Refine by chat or download <\/p>\n

Refine it by chat with follow-up instructions, or download it.<\/p>\n <\/div>\n <\/div>\n <\/div>\n <\/section>\n\n