Vincent Figure Large Model

Tencent HunyuanDiT recently released three new controllable plug-ins ControlNet with the community, namely tile (high-definition magnification), inpainting (image restoration and expansion) and lineart (line draft raw image), further expanding its ControlNet matrix. The addition of these plug-ins enables the HunyuanDiT model to cover a wider range of application scenarios, including art, creativity, architecture, photography, beauty and e-commerce, etc. 80% cases and scenarios provide more accurate...

In the wave of AI technology, the large-scale image model Kolors launched by Kuaishou has become a shining star in domestic AI technology with its excellent performance and open source spirit. Kolors not only surpasses the existing open source models in image generation effects, but also reaches a level comparable to commercial closed-source models, which quickly sparked heated discussions on social media. The open source road of Kolors The open source of Kolors is not only a technical milestone, but also a reflection of Kuaishou's open attitude towards AI technology. At the World Artificial Intelligence Conference, Kuaishou announced that Kolors was officially open source, providing a package…

During the ongoing World Artificial Intelligence Conference, Kuaishou Senior Vice President and Head of Main Site Business and Community Science Gai Kun announced that Kuaishou's large model of text-based images, Ketu, has been officially open sourced, hoping to build a more prosperous community ecosystem for the large model of text-based images. Kuaishou's "Ketu" large model was opened to the public in May this year. It has now been launched on the web version and WeChat mini-program, supporting two types of functions: text-based images and image-based images. It can be used for AI image creation and AI image customization. It was found that in the AI creation module, users only need to enter the description text and select the desired painting style to quickly obtain their own AI...

Tencent Hunyuan Wenshengtu Large Model (Hunyuan DiT Model) announced the full open source training code, including LoRA plug-in and ControlNet plug-in. LoRA is a technology for fine-tuning large language models. It can train a model with specific features using a small amount of data without modifying the original model or increasing the model size. ControlNet is a controllable generation algorithm that allows users to better control image generation by adding additional conditions. Tencent Hunyuan provides three first-run ControlNet models that can extract application-related...

Kuaishou's self-developed large-scale model of text and image, "Ketu", has been officially opened to the public recently. It currently supports two types of functions: text and image, and can be used for AI image creation and AI image customization. Users can use it through the "Ketu" WeChat applet and web version. According to Jiemian News, this is also the first time that Kuaishou has opened its self-developed series of large models to the public. The report quoted an insider as saying that the parameter scale of the "Ketu" large model is at the billion level. These data come from the open source community, Kuaishou's internal construction and self-developed AI technology synthesis, covering tens of millions of common Chinese entity concepts, and also introduces reinforcement learning and reward...