Unverified50% confidenceFactExact time
Meta Muse Spark Open's input modalities cover text, images, video and audio, and the degree of reasoning effort can be adjusted between low and xhigh.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedMuse Spark Open supports multimodal input of text, images, video and audio.79% similarUnverifiedMuse Glimmer has multimodal capabilities, with a built-in vision encoder that can accept both text and image inputs simultaneously61% similarUnverifiedMuse does not generate images or videos itself but instead calls Meta's models; the video quality is poor, character consistency cannot be maintained, and content filtering is overly strict.61% similarUnverifiedMuse Wonder accepts three input forms—text, images, and PDFs—and supports tool calling and structured output.61% similarUnverifiedThe Muse Wonder model card lists a 1-million-token context and support for text, image, video, and audio input, with text output.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1039700API
curl https://kongchang.com/api/v1/knowledge/claims/1039700MCP
get_claim(id=1039700)