Expired50% confidenceFactExact time
The Prompt API supports multimodal input; images can be processed by setting expectedInputs to type: image in the session options.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/18/2026
First Seen
Valid until: 10/16/2026(expired)
Sources
Related Claims
VerifiedAI 图像生成中通过视觉编码器（如 CLIP 模型）对输入产品照片进行特征提取，再结合文本提示词通过扩散模型逐步去噪生成目标图像70% similarUnverifiedJimeng AI's Agent mode supports dragging and uploading generated images and converting them into concept videos via instructions.70% similarUnverifiedTrae supports using images as conversation input, with three methods: drag-and-drop, paste, and button upload.70% similarUnverifiedThe multimodal conversational system supports three categories of image understanding capabilities: image content recognition, text extraction (OCR), and image-text question answering.70% similarUnverifiedIPAdapter（Image Prompt Adapter）允许用户通过提供参考图像来引导生成图像的风格、构图或主体特征69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/547905API
curl https://kongchang.com/api/v1/knowledge/claims/547905MCP
get_claim(id=547905)