Unverified50% confidenceFactExact time
Ojin offers two facial models: Portrait (a portrait model focused on scalability) and Presence (a presence model focused on expressiveness), sharing the same API interface.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/9/2026
First Seen
Valid until: 12/8/2026
Sources
Related Entities
Related Claims
UnverifiedOllama supports multimodal image understanding tasks and can invoke image recognition via the --image parameter.71% similarUnverified研究者使用Qwen-Image-Edit和HiDream O1两款生成模型制作合成图像，并将合成图与真实图像一同送入模拟真实平台环境的处理管线70% similarUnverifiedAfter three-view drawings (front, side, and back) are input as reference images, they can help AI anchor the visual characteristics of a character when generating new scenes, addressing the character consistency problem in generative AI.69% similarUnverifiedThe N2 model supports multimodal input and can understand screenshots and design drafts, allowing developers to directly provide the model with UI design draft screenshots or hand-drawn interface sketches.68% similarUnverified视觉模型接收每张屏幕截图并输出结构化信息，包括OCR识别文本、页面布局、UI控件的像素坐标框及元素状态68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/884042API
curl https://kongchang.com/api/v1/knowledge/claims/884042MCP
get_claim(id=884042)