Meta Platforms said on Tuesday it is rolling out Muse Image, its first image-generation model from ​Meta Superintelligence Labs, as the Facebook owner ‌expands generative AI tools across its apps.

The company said Muse Image, which is integrated into its Meta AI chatbot, can ​interpret complex prompts, use photos as inputs and ​let users edit generated images directly through ⁠sketches or annotations.

Meta said its Muse Image model will power more than 30 new AI effects for Instagram Stories and enable image generation in direct chats with Meta AI on WhatsApp, initially in select countries.

Read More: Meta’s Zuckerberg says AI agent tech progressing slower than expected

The company plans to expand Muse Image to more markets and integrate the technology into Facebook and Messenger.

While basic use of Muse Image through Meta AI will remain free, additional image creation capabilities will be offered through Meta’s subscription plans.

In April, Meta launched Muse Spark, the first text-and-reasoning AI model developed by its Meta Superintelligence Labs team, which was assembled last year as the company sought to compete with rivals in the artificial intelligence race.

Advanced AI models are driving the current AI boom, powering autonomous tasks such as software development, content generation and customer support operations.

Meta also announced an early preview of Muse Video, its AI model designed to generate videos.