Categories: News

Snap launches AI video tool for creators

At its annual Snap Partner Summit on Tuesday, Snapchat announced that it’s introducing a new AI video-generation tool for creators. The tool will allow select creators to generate AI videos from text prompts and, soon, from image prompts. 

Snap says the tool will be available in beta on the web starting today for a small subset of creators. For now, Snap doesn’t have any plans to make Snap AI Video available to anyone beyond creators.  

While the company didn’t share any additional details about the AI video-generation tool during the keynote, a spokesperson for the company told TechCrunch in an email that the tool is powered by Snap’s own foundational video models.

“We know it’s important for our community to be informed when AI is being used to generate content,” said Ceci Mourkogiannis, Snap’s vice president of product, during the keynote. “So we use icons and context cards to let you know when a Snap is made with Snap AI.”

Image Credits:Snap

All of the content created with Snap AI Video will include a watermark that will stay visible when content is downloaded and shared. 

A Snap spokesperson said the company’s models undergo safety evaluations and testing to prevent them from creating harmful content and that it has additional safety mitigations in place during the model training process, at prompt creation, and at the output stage.

Snap’s announcement puts it ahead of its social media peers, including TikTok and Instagram, which have yet to release text-to-video AI generators. Although Meta unveiled a tool called Make-A-Video back in 2022 that enables text-to-video generation, it hasn’t released it to the public. 

The company is likely hoping to go up against startups like Runway, along with popular companies like OpenAI and Adobe, both of which plan to release text-to-video AI generators to the public later this year. 

However, given that Snap hasn’t shared any examples of outputs from its AI video-generation tool, it’s unclear how its product will fare against these other tools. 

hbspt.forms.create({
region: “na1”,
portalId: “44101848”,
formId: “09f96578-8d24-4d8a-8e9f-7700cff83c29”
});

admage

Share
Published by
admage

Recent Posts

InstantIR: Restore Your Images

Figuring out the model that can fix your low quality pictures? Now, restoring your low…

4 days ago

Omnigen: Next-Gen Image Generation & Editing Tool

Traditional diffusion models uses various mechanisms for image modification like ControlNet, IP-Adapter, Inpainting, Face detection,…

1 week ago

Create Engaging Videos with Mochi1

Mochi 1, an open-source text-to-video diffusion model has been released by Genmo.  Trained with 10…

3 weeks ago

Local Installation of Stable Diffusion 3.5

So, it's finally here. Stable Diffusion 3.5 has been released by StabilityAI on October 22nd,…

4 weeks ago

Video Depth Mapper: Efficient 3D Depth Mapping Solution

Due to the extreme diversity of video content like motion, camera panning, and length, the…

1 month ago

Top 30 Negative Prompts for Reliable Diffusion Models

 You can use these negative prompts while generating images using Stable Diffusion models.1. Clear BrandingPrompt:text,…

1 month ago