Unverified50% confidenceSolutionExact time
Nebulae uses a method of inputting two views per page of drawing: the original text layer guarantees label accuracy, and the rendered image preserves the subordinate relationships between symbols and surrounding elements.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Get Image node's prompt reuses PhotoCraft's built-in Notes feature, and multiple notes are automatically concatenated.64% similarUnverifiedThe use of <image1> and <image2> placeholder syntax in the prompt is a specific input format for Qwen multimodal models, used to distinguish the roles of multiple input images.64% similarUnverified千问Image 2.0 Pro支持文生图和图生图两种模式，文生图通过语义理解逐步去噪生成图像，图生图在参考图的视觉特征约束下进行风格迁移或内容修改64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018340API
curl https://kongchang.com/api/v1/knowledge/claims/1018340MCP
get_claim(id=1018340)