OpenAI has developed a new AI model that can generate media content such as images, videos and audio 50 times faster than previous systems. The new model, called a “continuous-time consistency model,” takes about a tenth of a second to generate an image instead of the usual five seconds, OpenAI researchers Cheng Lu and Yang …
The research company Playground Research presents “Playground v3”, a new AI model for text-image generation, which has apparently achieved top performance in several test procedures. The system stands out for its precise implementation of text instructions, its ability to reason logically, and the outstanding quality of its text rendering. In user studies, the model even …
Artificial intelligence is making professional portrait photos possible without a photographer. Three AI services – Portrait Pal, PixelPose, and Dreamwave – turn simple photos into high-quality application photos, as Jon Stojan reports in an article for VentureBeat. The services differ primarily in price, processing time, and the number of photos delivered. The three services work …
The Canadian AI startup Ideogram has expanded its image generation capabilities with a new interactive “Canvas”. As reported by Carl Franzen, users can now arrange, compare, and combine AI-generated images on an unlimited workspace. The new tool includes features like “Magic Fill” for targeted image editing and “Extend” for expanding image boundaries. Ideogram offers Canvas …
The design platform Canva has launched a new AI image generator called “Dream Lab”. The tool, based on Leonardo.ai technology, can create images from text descriptions in various styles such as “3D render” or “illustration”, reports Jess Weatherbed. Compared to Canva’s existing Stable Diffusion generator, Dream Lab is said to deliver better results particularly in …
Stability AI has unveiled its latest family of image generation models: Stable Diffusion 3.5. According to the company, it includes three variants – Large, Large Turbo and Medium – that are said to be characterized by improved adaptability and versatility. The Large variant with 8 billion parameters is available immediately, while the Medium model is …
The AI image generation software ComfyUI has been released in version 1.0 and now offers a desktop version for Windows, MacOS and Linux. Background: ComfyUI allows you to implement complex image generation pipelines directly on your own computer. Unlike cloud-based solutions, the software provides full control over the process and your own data. The brand …
A new text-to-image framework called Sana can efficiently and quickly generate high-resolution images up to 4096 x 4096 pixels. The system uses a deep compression autoencoder, linear attention, and a decoder-based text encoder to optimize performance. According to the developers, Sana-0.6B can compete with state-of-the-art large diffusion models, but is 20 times smaller and over …
Adobe is unveiling experimental AI tools aimed at enhancing content creation, reports The Verge. These tools focus on automating tedious tasks in animation, image generation, and video editing, allowing users to achieve professional results without extensive experience. These innovations are presented as “Sneaks,” which are in-development projects to gauge public interest, though not all will …
The image editing platform PicsArt is more than a decade old at this point and is now focusing on “contextual intelligence” and AI agents to stand out in this competitive market, reports Shubham Sharma from VentureBeat. Instead of adding new features, PicsArt CTO Artavazd Mehrabyan explains that the company is prioritizing improving the quality of …