Unverified50% confidenceFactExact time
Decision 3.0 can process text and images simultaneously in a single call
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
Unverified参考图像功能每次生成提供3个备选方案68% similarUnverifiedThe integrated package includes image generation and editing workflows, with the model capable of 4K direct output and supporting localized editing via instruction commands.66% similarUnverifiedThis multimodal workflow consists of three stages, each with a distinct role: an image generation model, a coding agent, and a browser tool.64% similarUnverifiedThe multimodal vision Agent feeds the actual rendered result of the front-end page back to the model via screenshots, forming a closed loop of screenshot → analysis → prompt modification → regeneration, which is the core advantage over pure text models.64% similarUnverified官方推荐的工作流是先用图像模型制作和编辑第一帧，达到图像级画质后再喂给 H3 做动画化63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999812API
curl https://kongchang.com/api/v1/knowledge/claims/999812MCP
get_claim(id=999812)