Figure 1

On January 27th, a message was sent to the Mixer (January 26) to publish a Mixed Image 3.0-Instruct model, which supports image editing and multi-mixing, and goes online in parallel with the Equestrian Treasure, where users can experience it directly at the end of the Mixer and at the Quantuan Network. Mixtures Image 3.0 Total Parameters of Maps 8 billion (Activating Parameters around 1.3 billion), using a hybrid specialist (MoE) structure, based on the original multi-modular structure basic model of Mixtures Image 3.0, introducing multi-task data of the Graphics through..

First of all, the diagram to generate a diagram is to generate another diagram based on a diagram. Let's take the Kontext function we talked about last time as an example ComfyUI User's Guide, HandyUI Teaches You to Write Prompt Words to Generate Pictures with Flux Kontext Kontext can remove watermarks from a picture by a single sentence, extract elements from a picture, make precise modifications to the localization, transform the style of a picture, change the angle of a person in a picture, and so on. Of course, Kontext is a very powerful model, its features in previous articles we...

On December 26th, the official public number of "Step-1X" published a blog post yesterday (December 25th), announcing the launch of Step-1X-Medium enhanced AI model, which significantly improves the generation speed, comprehension ability, detail texture and creation function, aiming to become the creator's right-hand man. The upgraded model is able to more accurately understand user commands and generate images that better meet the needs of the work, and it has added richer creation games such as "picture-to-picture" matting and style migration, further lowering the threshold of creation. StageStar launched the image generation model St....