Xunfei Xinghuo Cognitive Model Upgrade Experience

Today, the new version of Xunfei Xinghuo has been updated to the live network, adding many functions such as multi-modality and plug-ins~, read the original text and apply for experience

Official website address: https://xinghuo.xfyun.cn/

Multimodal Capabilities

1. Multi-modal understanding (picture): Support user picture input, and perform visual question-and-answer for the content of the picture.
   

2. Image generation: According to the user's description, generate an image that meets the requirements.
   

3. Virtual human video generation: According to user requirements, generate a virtual human video that meets the requirements.
   

4. Audio generation: According to user requirements, generate synthetic audio that meets the requirements, and automatically match the speakers.
   

5. OCR note collection: OCR results of document images, support one-click collection, and automatically summarize titles and abstracts.
   

Assistant mode update:

1. Assistant structured instructions: Help users quickly customize their own exclusive assistants through fields such as role setting, goal tasks, requirement descriptions, style settings, and improve the effect of the assistant's large-scale model application
   

2. Personal datasets: Users can create datasets and link them to the assistant for question-and-answer.
   

3. Stand-alone web application: A single assistant can be shared as a stand-alone web application.
   

4. Assistant API: Each assistant automatically generates an independent API to help developers quickly integrate the assistant into their own applications
   

plug-in capability

1. Document question and answer: a powerful knowledge question and answer tool, upload documents, and ask questions.
   

2. PPT generation: Simple and efficient, quickly generate PPT presentations.

生成一个年度总结ppt

The prepared PPT can be downloaded

3. Resume generation: Enter keywords such as positions and personal information to automatically generate resume documents.

我叫张星火，性别男，有3年产品经理经历，请帮我生成一份简历模版

Other functions

1. Avatar and nickname: Support users to change the avatar and nickname.
   

2. Personal information: Support users to improve their personal information

3. Self-training speakers: users can quickly create and train their own speakers
   

4. Dialect speakers: 3 new official dialect speakers

5. Share continuation: Support users to share their own conversation content in the form of page links, and other users can click on continuation to automatically bring the shared conversation content into their own conversation to continue the conversation.
   

In addition, the registration and login questionnaire process has been greatly simplified~