ElevenLabs Integrates FLUX.2 Into Image & Video Product for 4MP AI Visuals.

ElevenLabs has integrated FLUX.2, the latest image model from Black Forest Labs, into its Image & Video product. The addition brings significant upgrades to resolution, consistency, and generation speed for users creating AI-generated visuals.

The announcement, shared on LinkedIn, signals a continued push by ElevenLabs to expand beyond its core voice AI capabilities. While the company is best known for text-to-speech and conversational agents, it has been gradually building out creative tools for video and image generation, most recently partnering with Meta to power AI audio across Instagram and Horizon.

FLUX.2 introduces several technical improvements over earlier models. Multi-reference image input allows users to maintain consistent characters and products across multiple generated images, a common pain point in AI workflows where visual consistency often breaks down. The model also delivers better real-world lighting and spatial accuracy, which should reduce the uncanny or artificial look that plagues many AI-generated images.

Resolution support now extends to 4MP, offering flexible output sizes that can adapt to different use cases, from social media graphics to larger marketing assets. Generation speeds have been pushed to under 10 seconds, making the tool more practical for iterative workflows where users need to test variations quickly.

These capabilities position ElevenLabs as a more viable option for teams needing both audio and visual assets in a single platform. Competitors like Midjourney focus exclusively on image generation, while Canva offers broader design tools but with less sophisticated AI generation. ElevenLabs is carving out a middle path, bundling creative AI tools under one roof for users who want audio, voice, and now high-quality visuals without switching platforms.

The FLUX.2 integration continues a pattern of strategic product expansion. ElevenLabs has been methodically adding features outside its original domain. Earlier this year, the company launched AI agents for WhatsApp, enabling businesses to deploy conversational AI across messaging platforms. It also introduced voice chat for books, allowing readers to interact with AI narrators that understand story context.

The company raised a $500 million Series D at an $11 billion valuation in February, according to its official blog. That funding round underscored investor confidence in ElevenLabs' ability to grow beyond audio into adjacent AI verticals. The FLUX.2 integration suggests the company is using that capital to build a more comprehensive creative suite, rather than doubling down exclusively on voice technology.

For small business owners and content creators who already use ElevenLabs for voiceovers or AI agents, the addition of FLUX.2 means fewer tools in the stack. Instead of juggling Midjourney for images, Descript for video editing, and ElevenLabs for audio, teams can consolidate more of their workflow in one place.

FLUX.2 is available now inside ElevenLabs Image & Video. The company has not disclosed whether the feature requires a specific subscription tier or if it will be rolled out to all users.