AI image model

There's fun again! Qwen launched a new image generation and editing model. This is called Z-Image. I'm going to summarize this model, which is "light, fast, good and right." Translation is that the computer configuration requirements are low, very fast, very effective, manageable and open-ended. No more information is given here. Say more than play. The next hand is to teach you to install the configuration and to pull it directly to the end! The software download upgrade to run this thing, it's simple..

Recently, some students have asked what are some good AI raw image and video model applications that are accessible in China? Today, I will give you a relatively comprehensive introduction to the recently commonly used domestic AI raw image model application - Jimeng AI. At present, you can get points for free to perform a certain number of raw image and video operations by logging in to Jimeng AI every day. I got 60 points when I logged in today. PS: The free trial policy may be adjusted at any time in the future. Next, let's learn about Jimeng's introduction, R&D team, functional features, and usage methods. This article will take you to understand the AI raw image model Jimeng official website Jimeng AI official website address: https://ww…

Recently, some students have asked how to use Midjourney. Before the web version of Midjourney was released, I wrote an article that required using Discord to use Midjourney. For detailed tutorials, see the article: This article takes you through the process of logging in to using Midjourney (with practical instructions) On August 16, 2024, Midjourney released a web version. Like most AI image generation websites, you can directly generate images by entering prompt words. PS: Before that, you need to download Discord to use it, which is a bit…

On August 1, 2024, the Black Forest Lab was officially established and released the FLUX.1 model suite. This month, I have seen many AI learning enthusiasts, entrepreneurs, and self-media introduce and train based on FLUX.1 raw images and Lora. The raw image effect is really great. I took advantage of this weekend to do some study, sorting, and testing research on FLUX. Let's see the effect first. The following are some of the image effects generated online based on the [FLUX.1 Miles Online Runnable-Dark Forest Studio FLUX.1-dev-fp8] model on LiblibAI. Next, let's learn together...

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...