New Tech from MIT, Adobe Advances Generative AI Imaging

Researchers from the Massachusetts Institute of Technology and Adobe have unveiled a new AI acceleration tool that makes generative apps like DALL-E 3 and Stable Diffusion up to 30x faster by reducing the process to a single step. The new approach, called distribution matching distillation, or DMD, maintains or enhances image quality while greatly streamlining the process. Theoretically, the technique “marries the principles of generative adversarial networks (GANs) with those of diffusion models,” consolidating “the hundred steps of iterative refinement required by current diffusion models” into one step, MIT PhD student and project lead Tianwei Yin says. Continue reading New Tech from MIT, Adobe Advances Generative AI Imaging

Midjourney Creates a Feature to Advance Image Consistency

Artificial intelligence imaging service Midjourney has been embraced by storytellers who have also been clamoring for a feature that enables characters to regenerate consistently across new requests. Now Midjourney is delivering that functionality with the addition of the new “–cref” tag (short for Character Reference), available for those who are using Midjourney v6 on the Discord server. Users can achieve the effect by adding the tag to the end of text prompts, followed by a URL that contains the master image subsequent generations should match. Midjourney will then attempt to repeat the particulars of a character’s face, body and clothing characteristics. Continue reading Midjourney Creates a Feature to Advance Image Consistency

Stability AI Advances Image Generation with Stable Cascade

Stability AI, purveyor of the popular Stable Diffusion image generator, has introduced a completely new model called Stable Cascade. Now in preview, Stable Cascade uses a different architecture than Stable Diffusion’s SDXL that the UK company’s researchers say is more efficient. Cascade builds on a compression architecture called Würstchen (German for “sausage”) that Stability began sharing in research papers early last year. Würstchen is a three-stage process that includes two-step encoding. It uses fewer parameters, meaning less data to train on, greater speed and reduced costs. Continue reading Stability AI Advances Image Generation with Stable Cascade

Apple Launches Open-Source Language-Based Image Editor

Apple has released MGIE, an open-source AI model that edits images using natural language instructions. MGIE, short for MLLM-Guided Image Editing, can also modify and optimize images. Developed in conjunction with University of California Santa Barbara, MGIE is Apple’s first AI model. The multimodal MGIE, which understands text and image input, also crops, resizes, flips, and adds filters based on text instructions using what Apple says is an easier instruction set than other AI editing programs, and is simpler and faster than learning a traditional program, like Apple’s own Final Cut Pro. Continue reading Apple Launches Open-Source Language-Based Image Editor

Unpacked: Samsung Intros Galaxy AI with Next Gen S Phones

During this week’s Unpacked event, Samsung introduced Galaxy AI, a suite of artificial intelligence tools designed for the new Galaxy S series smartphones — the Galaxy S24, Galaxy S24+, and Galaxy S24 Ultra. “AI amplifies nearly every experience on the Galaxy S24 series,” including real-time text and call translations, a powerful suite of creative tools in the ProVisual Engine and a new kind of “gestural search that lets users circle, highlight, scribble on or tap anything onscreen” to see related search results. The AI enhancements are largely enabled by a multiyear deal with Google and Qualcomm. Samsung also debuted a wearable accessory, the Galaxy Ring. Continue reading Unpacked: Samsung Intros Galaxy AI with Next Gen S Phones

CES: Getty Rolls Out iStock Generative AI Powered by Nvidia

Getty Images and Nvidia are expanding their AI partnership with the addition of the text-to-image platform Generative AI by iStock, designed to produce stock photos that can be used by individuals or enterprise customers. Built on Nvidia Picasso, a foundry for custom AI models, and trained exclusively on data from Getty Images’ proprietary creative libraries, Generative AI by iStock “has been engineered to guard against generations of known products, people, places or other copyrighted elements,” Getty explains, adding that “any licensed visual that a customer generates comes with iStock’s standard $10,000 USD legal coverage.” Continue reading CES: Getty Rolls Out iStock Generative AI Powered by Nvidia

Stability AI Is Offering Paid Membership for Commercial Users

As the pressure ratchets up for AI companies to go beyond the wow factor and make money, Stability AI has formalized three subscription tiers as it seeks to expand commercial use of its open-source, multimodal core models. The Stability AI Membership offerings include a free tier for personal and research (i.e., non-commercial) use, a professional tier that costs $20 a month, and a custom-priced enterprise tier for large outfits. The company says that with the three tiers it is “striking a balance between fostering competitiveness and maintaining openness in AI technologies.” Continue reading Stability AI Is Offering Paid Membership for Commercial Users

Standalone Image Generator Is Among New AI Tools by Meta

Meta Platforms is moving Imagine with Meta from its test bed as a generative AI experience in chats to a standalone experience on the Web that allows users to create high-resolution images using natural language text prompts. That is one of more than 20 generative AI features Meta is deploying to create new business opportunities globally leveraging AI across search, ads, business messaging and more. While most will wind up on Facebook, Instagram, Messenger and WhatsApp, some say Meta’s popular Facebook and Instagram platforms have plateaued at 2 to 3 billion users per month, circumscribing ad growth. Continue reading Standalone Image Generator Is Among New AI Tools by Meta

Stability AI Intros Real-Time Text-to-Image Generation Model

Stability AI, developer of Stable Diffusion (one of the leading visual content generators, alongside Midjourney and DALL-E), has introduced SDXL Turbo — a new AI model that demonstrates more of the latent possibilities of the common diffusion generation approach: images that update in real time as the user’s prompt updates. This feature was always a possibility even with previous diffusion models given text and images are comprehended differently across linear time, but increased efficiency of generation algorithms and the steady accretion of GPUs and TPUs in a developer’s data center makes the experience more magical. Continue reading Stability AI Intros Real-Time Text-to-Image Generation Model

Stability Introduces GenAI Video Model: Stable Video Diffusion

Stability AI has opened research preview on its first foundation model for generative video, Stable Video Diffusion, offering text-to-video and image-to-video. Based on the company’s Stable Diffusion text-to-image model, the new open-source model generates video by animating existing still frames, including “multi-view synthesis.” While the company plans to enhance and extend the model’s capabilities, it currently comes in two versions: SVD, which transforms stills into 576×1024 videos of 14 frames, and SVD-XT that generates up to 24 frames — each at between three and 30 frames per second. Continue reading Stability Introduces GenAI Video Model: Stable Video Diffusion

Stability AI Adds Apps to Draft 3D Models, Fine-Tune Objects

Stability AI is rolling out next-generation enterprise tools for its Stable Diffusion text-to-image generator. Leading the pack is Stable 3D, geared toward game developers and  graphic designers, with results that integrate with popular 3D platforms including Blender, Maya, Unreal Engine and Unity, according to Stability. Now in private preview, Stable 3D enables non-experts to generate “thousands of 3D objects per day” by selecting an image or illustration or writing a text prompt. Another preview app, Stable FineTuning, provides the ability to quickly fine-tune pictures, objects and styles. A third tool, Sky Replacer, is available now. Continue reading Stability AI Adds Apps to Draft 3D Models, Fine-Tune Objects

Google Debuts Generative AI Tools Aimed to Help Merchants

Google is rolling out a suite of AI-powered marketing tools designed to help small businesses make the most of the holiday sales season. Merchants can add a “small business” attribute to their Search and Maps results and generate advertising and promotional materials using something called Product Studio. “Eighty-four percent of people say supporting local and/or small businesses is important to them, so we’re making it easier to find them on Google,” the company writes. Products and businesses with the “small business” label “will make it easier for shoppers to narrow down their searches and be intentional about shopping.” Continue reading Google Debuts Generative AI Tools Aimed to Help Merchants

OpenAI’s Latest Version of DALL-E Integrates with ChatGPT

OpenAI has released the DALL-E 3 generative AI imaging platform in research preview. The latest iteration features more safety options and integrates with OpenAI’s ChatGPT, currently driven by the now seasoned large language model GPT-4. That is the ChatGPT version to which Plus subscribers and enterprise customers have access — the same who will be able to preview DALL-E 3. The free chatbot is built around GPT-3.5. OpenAI says GPT-4 makes for better contextual understanding by DALL-E, which even in version 2 evidenced some glaring comprehension glitches. Continue reading OpenAI’s Latest Version of DALL-E Integrates with ChatGPT

OpenAI’s Altman Talks Up Machine Learning on Global Tour

Amidst calls to put the brakes on large language model development, OpenAI CEO Sam Altman has hit the global circuit to tout the advantages of artificial intelligence and commercial opportunities with his firm. Altman’s 17-city tour includes stops in Washington D.C., Toronto, Tokyo, Rio De Janeiro, Lagos, London, Paris, Madrid, Brussels, Munich, Tel Aviv, Singapore, Dubai, New Delhi, Jakarta, Seoul and Melbourne. On Monday, Altman met with Japanese Prime Minister Fumio Kishida and other government officials, vowing to collaborate on protecting user privacy and data protection. Continue reading OpenAI’s Altman Talks Up Machine Learning on Global Tour

Microsoft Introduces Visual AI Tools to Bing, Edge Platforms

Microsoft is bringing Bing Image Creator to the new Bing search engine and Edge browser. Powered by an advanced version of the DALL-E model from OpenAI, the new tools will allow users to generate images using word prompts to describe what they want to want to create. The news comes as Microsoft says its new Bing AI Copilot has had “more than 100 million chats to date,” with people using it to refine answers to complex questions or as entertainment or creative inspiration. Bing data indicates images are one of the most searched categories, second only to general web searches, according to Microsoft. Continue reading Microsoft Introduces Visual AI Tools to Bing, Edge Platforms