Transformers have brought tremendous advancements to various natural language tasks and have recently begun to penetrate the field of computer vision, starting to show potential in tasks previously dominated by CNNs. A recent study from the University of California, San Diego, and Google Research proposed using visual Transformers to train GANs. To effectively apply this … Read more
Janus-Pro is an advanced multimodal understanding and generation model developed by the DeepSeek-AI team, which is an upgraded version of the previous Janus model. Janus-Pro has improved in three aspects: optimized training strategies, expanded training data, and increased model scale. These improvements have enabled Janus-Pro to achieve significant progress in multimodal understanding and text-to-image instruction-following … Read more
Click the “Blue Word” to Follow Us In recent years, significant progress has been made in the field of artificial intelligence, especially in the area of multimodal models. Multimodal models can process and understand various types of data, such as text and images, simultaneously, greatly expanding the application scenarios of AI. The latest model released … Read more
Click the blue text Follow us 01 Introduction Following the successful launch of DeepSeek-V3 and DeepSeek-R1, DeepSeek has introduced an enhanced version of the Janus multimodal model, Janus-Pro, continuing to push the boundaries of artificial intelligence. In the rapidly evolving field of AI, multimodal models that can seamlessly understand and generate text and image content … Read more
Happy New Year, friends! I wish you good health and success in the new year! The wave of AI technology is continuously advancing, and 2025 is expected to be a year of explosive growth. I hope you keep an eye on the new technological industrial transformation in the coming year. Recently, the Janus-Pro model launched … Read more
Hello everyone, I am Qinghe. I have been working full-time in the internet industry for 8 years and have spent 5 years on Xianyu. Currently, I am a core member of Xu Xu’s AI team. I work full-time on AI video, leading team members in traffic generation, marketing, and monetization, helping them achieve transformation on … Read more
If you find Uncle Niu’s article useful, remember tolike,followoh! Your likes and follows are my motivation to continue creating! A couple of days ago, a group friend asked in the group how to make this kind of video where a beautiful woman transforms into an animal, shocking the judges on Britain’s Got Talent. This type … Read more
Hi, students! This is the 59th issue of our AI project tutorial – an introduction to Runway’s video subtitle processing and AI drawing features. It feels like it’s all set up just for making movies, with a complete set of features now online! A must-save for those who want to learn systematically! After in-depth research … Read more
1. Introduction to the Three AI Image Generation Websites 1. Tongyi Wanxiang: Officially launched on July 7, 2022 https://wanxiang.aliyun.com/ 2. Wenxin Yige: Officially launched on August 19, 2022 https://yige.baidu.com/ 3. 360LoRA: Officially launched on June 13, 2023, recently renamed to LoRA. https://lora.360.com 2. Image Generation Results Comparison Teacher: Generate a cute gray kitten jumping, with … Read more
Recently, interesting works in the AIGC community have emerged one after another, thanks to the success of Diffusion Models. As an emerging topic in generative AI models, diffusion models have brought us many surprises. However, it is important to note that current text-to-image diffusion models require large-scale text-image paired datasets for pre-training, making it very … Read more