Hey! Hello everyone! I'm Xiaoluo, today we're going to talk about a topic that has been around for a long time - AI model! Did you know that AI models are flourishing now, and each model has its own unique characteristics. At 2 pm on August 15th, HKUST Xunfei held a grand new product launch conference, and they officially launched a product called "Xunfei Xinghuo Cognitive Model". So, what kind of experience will this new model bring us? I will take everyone to reveal the secret now!
Xunfei Xinghuo can provide multi-scenario text generation, language understanding, knowledge question and answer, logical reasoning, mathematical answering, code generation and multi-modal capabilities based on natural text and voice, and quickly generate text, pictures, codes and other content.
Featured function display:
In terms of multimodality, Xunfei Xinghuo has also made a new update this time, supporting the picture questioning function and providing a visual "data fine-tuning" feature function, which is currently not available on GPT-4. Users can send a picture to Xunfei Xinghuo, and then ask Xunfei Xinghuo questions according to the content of the picture.
The following will give you an in-depth interpretation of the main features of Xunfei Xinghuo:
1. Image generation: According to the user's description, generate an image that meets the requirements.
2. Image understanding: Support user image input, and perform visual questions and answers on image content.
3. Virtual human video generation: According to user requirements, generate a virtual human video that meets the requirements.
4. Code ability: Provides powerful code generation, interpretation, and error correction functions.
5. Assistant function upgrade:
- 1.) Help users quickly customize their own exclusive assistant through fields such as role setting, goal task, requirement description, style setting, and improve the application effect of the assistant's large model.
- 2) Personal datasets: Users can create datasets and link them to the assistant for question-and-answer.
- 3) Independent web application: A single assistant can be shared as an independent web application.
- 4) Assistant API: Each assistant automatically generates an independent API to help developers quickly integrate the assistant into their own applications. **
6. Plug-in function: Three powerful plug-in functions can be selected in the dialog box, document question and answer, PPT generation and resume generation.
Next, I will introduce each function in detail:
1. Generate pictures from text
Xunfei Xinghuo is a multi-modal output model that supports text to generate images directly. Although this function is not as delicate as Midjourney, it can basically understand the user's intentions and generate high-quality pictures. For example, generate a back view photo of a girl by the sea under the sunset.
Generate an AE86 galloping through the night.
2. Picture understanding
Picture questioning is one of the main features of Xunfei Xinghuo. As early as March this year, when OpenAI released GPT-4, it showed that this function has not been opened until now. Now, you can experience it on Xunfei Xinghuo.
Imagine you took a photo or saw an interesting image online, have you ever wanted to know more about it? Is there a strong curiosity that drives you to understand it? Then, Xunfei Xinghuo can help you answer this question!
For example, upload a landscape photo and let him interpret it.
3. Virtual human video generation
This function can generate a virtual human video that meets the requirements according to the text prompt. For example, help me generate a birthday greeting video.
4. Multi-scene text generation
In order to meet the needs of different users, Xunfei Xinghuo provides an assistant center that can be used in rich scenarios, which can provide more in-depth and professional text creative functions according to fields such as workplace, marketing, life, recruitment, programming, and customer service.
Including title generation, mock interview, story creation, scenic spot recommendation, etc., suitable for Xiaohongshu, Douyin, Weibo, Kuaishou and other platforms, it is very convenient to use just by clicking.
5. Code generation, interpretation, and error correction functions
Xunfei Spark provides powerful code generation, interpretation, and error correction functions. For example, write a front-end page with HTML+css, and quickly give a simple example, and explain in detail the operating principle, call, and operating principle of the code.
The results of running and debugging are as follows:
6. Powerful plug-in function
What I am most interested in is the new plug-in function this time. This is really a good thing. There is a plug-in function to select after the new dialogue of the spark model
Here you can choose plugins such as document Q&A, ProcessOn, PPT generation or resume generation
PPT template generation, for example, to generate a sales PPT template, users can directly download the generated PPT template on the platform.
Resume generation, for example, hello, my name is Xiaoluo, I am a fresh graduate, graduated from Taiyuan University of Technology, good at C++, Java, JS, database and other languages, I want a back-end development game position, I have one year Development experience, help me generate a resume
assistant mode
There is another function that is also very good. They have also updated the assistant mode in this update.
You can quickly customize your own exclusive assistant through role setting, or you can create your own data set and link it to the assistant to ask questions, which means that you can independently train an assistant that belongs to you, your background, business, demands, etc. You can use this assistant to train and finally turn it into an assistant that belongs only to you.
Write at the end:
I watched the whole conference online this time, and it can be said that I was very excited. Every function made my eyes shine, especially the picture understanding function. Although there is no real "intelligence", I believe that Xunfei The day of Xinghuo will come soon, and it will also be a breakthrough with trans-epochal significance.
Finally, I contacted the staff of HKUST XFLYTEK to apply for the exclusive internal test qualification and exclusive benefits for everyone. The link is as follows: Early access https://xinghuo.xfyun.cn/?ch=bl_sxgzO3
1. Through my [exclusive] Link] The link application experience is faster (5 minutes at the fastest, 4 hours at the slowest), and it is strongly recommended to apply through the exclusive link; 2.
Developer rights and benefits: Applying through the blogger's exclusive link can also have a higher Spark The large model API test quota is 30% more than the ordinary channel application, and the maximum can apply for 500w Tokens.
What are you waiting for, hurry up and experience~