Ketu

December 27th news, fast hand today announced, can figure 1.5 image model released, the quality of the screen and aesthetics greatly improved. ai try on new "AI model" function, enter the text description can be generated AI model, with AI dress and can Ling 1.6 graphic video, can generate clothing display video. In addition, under the high-quality mode of Keyline 1.5 model (Note: graph-generated video), it supports the function of "tail-frame generation". After uploading pictures, switch the pictures to the position of "tail-frame picture", and then generate 5s/10s videos based on the tail-frame forward without uploading the first picture. After uploading the image, switch the image to the "Tail Frame" position, and you can generate 5s/10s video based on the tail frame forward without uploading the first image. ...

Want to try out the latest fashion trends in the comfort of your own home, but don’t want to worry about the wrong size and color? Kolors Virtual Try-On app is here to help! This cutting-edge technology app allows users to easily try on various clothes and enjoy a personalized fashion experience without leaving the sofa. Users only need to upload their own photos, and Kolors Virtual Try-On will generate a virtual fitting room. Here, users can try out various styles, from casual to formal, from daily wear to dinner dresses. The clothing library in the app has everything to meet your needs...

I have been looking for an AI model that can add Chinese characters to a text image, but I haven't found one that meets my expectations. Although MJ, SD, and Ideogram can add English to images well, adding Chinese characters to them will turn into garbled text. When I read the introduction of the Kolors open source project today, I found that Kolors's effect of adding Chinese characters to a text image was good, so I couldn't help but do a test immediately. Let's look at the effect prompt words first: a photo of a ladybug, macro, zoom, high quality, movie, the ladybug is holding a wooden sign with the words "Learn AI with Guotou" written on it, and below it...

Kuaishou has made a big move by open-sourcing its own image generation model, "Ketu Kolors". This is not an ordinary model. It has been trained on billions of text-image pairs, equipped with a general language model (GLM) as a text encoder, supports bilingual prompts in Chinese and English, and can handle contexts up to 256 tokens. Ketu Kolors features at a glance: Bilingual support in Chinese and English: Using the general language model (GLM) as a text encoder, the model is not only proficient in English, but also can perfectly understand and use Chinese prompts. Long article…

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...

Recently, Kuaishou's large-scale model product "Ketu" was officially launched. Users can enter the free trial through the Ketu platform and Ketu mini program. The functions launched this time include Wenshengtu and AI image customization (anime avatars, realistic portraits). After a simple experience, it feels similar to ByteDance's "Xinghui", but because it has just been launched, the current picture theme styles are less than Xinghui. Its highlight is mainly the comic avatar, which has richer theme styles than Xinghui. Let's take a look at the functional content of the Ketu (KOLORS) platform and mini program. The homepage of the Ketu (KOLORS) computer terminal mainly includes A…

Kolors is an AI image generation tool independently developed by Kuaishou. It is a free AI image generation platform launched by Kuaishou. It is based on Kuaishou's self-developed text-generated image model "Kolors Big Model", with a parameter scale of billions. It supports two major functions: text-generated image and image-generated image, and provides more than 20 AI image gameplays. Kolors can be used for AI image creation and AI image customization. This AI image generation tool has powerful text understanding, rich detail depiction and diverse style conversion capabilities. Relying on the self-developed Chinese CLIP model and big model, it has achieved a deep understanding of Chinese concepts...

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...