Meta Muse Image
Meta Superintelligence Labs' agentic image model, which plans a layout and calls search and coding tools before it renders, for prompt-faithful generation, multi-reference composition and precise local edits.
Muse Image is a cloud image-generation model built by Meta. It generates images from a text prompt, and can take reference images to guide style or composition (image-to-image). It supports 8 aspect ratios. Images can be saved as PNG, JPEG, and WebP. It runs through Runware using your own API key, from about $0.01 per image.
- Released
- Jul 2026
- Pricing
- $0.01 per image
- Aspect ratios
- 1:1, 16:9, 9:16 +5 more
- Image-to-image
- Up to 10 reference images
- Output formats
- PNG, JPEG, WebP
Samples
Generated with Muse Image via Runware. The same three prompts run against every model in the catalog, first result kept, so the only thing that changes between two models’ tiles is the model.
Materials, reflections, macro detail
Skin texture, lighting, shallow depth of field
Text rendering, layout, flat colour
Meta
Meta's FAIR and GenAI labs build the open-weight Llama family of language models — among the most widely used open models for local inference.
ai.meta.com ↗Meta's frontier reasoning model for complex personal and professional agentic tasks, with image input, tool calling and a 1M-token context window.
Meta's multimodal reasoning model for long-running agentic, multi-agent and coding workflows, with image input and a 1M-token context window.
Meta's open-weight multimodal reasoning model (816B total, 42B active parameters) built for agentic coding, with image input and a 1M-token context window.
Meta's speech-to-text model for push-to-talk and speaker-aware transcription, which returns plain text.
Meta's 1B instruction-tuned model — the smallest Llama, runnable in-process via HuggingFace or through Ollama.
Meta's 8B instruction-tuned model with 128K context and strong general reasoning.