Introducing Muse Image and Muse Video
Muse Image follows instructions faithfully, edits with precision, composes from multiple references, and draws on Instagram for social context. Muse Video delivers exceptional visual fidelity with native audio support. We're excited to launch Muse Image and preview Muse Video, the first media generation models developed by Meta Superintelligence Labs.
Key Takeaways
- Muse Image is our most advanced image generation model yet: it follows instructions faithfully, edits with precision, composes from multiple references, and draws on Instagram for social context.
It also brings agentic tool use capabilities and integrates with Muse Spark.
- Muse Image also integrates with Muse Spark, allowing the two models to share tools and plan jointly for powerful agentic media generation.
During reinforcement learning, Muse Image learns to write and execute code that produces accurate plots and QR codes, and condition on rendered figures to improve the accuracy of generated images.
- We didn't design this behavior.
Instead, it emerged during RL training simply because self-refinement produced better images and therefore higher reward.
- Notably, this compute spans two very different kinds of work - text tokens for reasoning, visual tokens for generation - yet quality is a function of the combined total compute.
We find that using the token budget judiciously matters just as much for effective test-time scaling.
- It can follow a variety of instructions as our examples show.
Continue Learning
Comments
Sign in to join the conversation