Latest news with #imagegeneration
TechCrunch
2 days ago
- Business
- TechCrunch
Black Forest Labs' Kontext AI models can edit pics as well as generate them
Black Forest Labs, the AI startup whose models once powered the image generation features of X's Grok chatbot, on Thursday released a new suite of image-generating models — some of which can both create and edit pics. The most capable of the models in the new family, called Flux.1 Kontext, can be prompted with text and, optionally, a reference image to create new images, writes Black Forest Labs in a blog post. 'The Flux.1 Kontext models deliver state-of-the-art image generation results with strong prompt following, photorealistic rendering, and competitive typography — all at inference speeds up to 8x faster than current leading models,' the company writes in its post. Flux.1 Kontext comes as the race to build competitive image generators heats up. Google debuted its latest image-generating model, Imagen 4, earlier this month at the company's I/O developer conference. Earlier this year, OpenAI brought a vastly improved image-generating model to ChatGPT — a model that quickly went viral for its ability to create art in the style of Studio Ghibli movies. Today we're releasing FLUX.1 Kontext – a suite of generative flow matching models that allow you to generate and edit images. Unlike traditional text-to-image models, Kontext understands both text AND images as input, enabling true in-context generation and editing. — Black Forest Labs (@bfl_ml) May 29, 2025 There's two models in the Flux.1 Kontext family: Flux.1 Kontex [pro] and Flux.1 Kontex [max]. The former allows users to generate an image and refine it through multiple 'turns,' all while preserving the characters and styles in the images. Flux.1 Kontex [max] focuses on speed, consistency, and adherence to prompts. Hello FLUX.1 Kontext! Kontext is a new state-of-the-art image editing model from Black Forest Labs. It's live now on Replicate. You can edit images with words: Change clothes, restyle scenes, rewrite text, all from a prompt. It just works 🔥 Pro and Max:… — Replicate (@replicate) May 29, 2025 Unlike some of Black Forest Labs' previous models, Flux.1 Kontex [pro] and Flux.1 Kontex [max] can't be downloaded for offline use. However, Black Forest Labs is making an 'open' Kontext model, Flux.1 Kontext [dev], available in private beta for research and safety testing. Black Forest Labs is also launching a model playground that allows users to try its models without having to sign up for a third-party service. New users get 200 credits, enough to generate around 12 images with Flux.1 Kontex [pro]. Techcrunch event Save now through June 4 for TechCrunch Sessions: AI Save $300 on your ticket to TC Sessions: AI—and get 50% off a second. Hear from leaders at OpenAI, Anthropic, Khosla Ventures, and more during a full day of expert insights, hands-on workshops, and high-impact networking. These low-rate deals disappear when the doors open on June 5. Exhibit at TechCrunch Sessions: AI Secure your spot at TC Sessions: AI and show 1,200+ decision-makers what you've built — without the big spend. Available through May 9 or while tables last. Berkeley, CA | REGISTER NOW Black Forest Labs, based in Germany, was said to be in talks to raise $100 million at a $1 billion valuation toward the end of last year. Many of the founders hail from Stability AI, the creator of the notorious Stable Diffusion image-generating model. Backers include Andreessen Horowitz, Oculus co-founder Brendan Iribe, and Y Combinator's Garry Tan. In the months since it emerged from stealth, Black Forest Labs has released a number of new image-generating models and enterprise-focused services including an API.
CNET
5 days ago
- Business
- CNET
ChatGPT Image Generator Is in Microsoft Copilot Now: What You Can Do With It
Microsoft has introduced significant enhancements to its Copilot AI assistant, integrating OpenAI's GPT-4o model to support advanced image generation capabilities. The update lets you create detailed visuals directly within Microsoft 365 applications, including Word, Excel and Outlook, by simply describing your desired image. Here's everything you need to know. What is the Microsoft Copilot AI assistant? Microsoft Copilot is an AI-powered assistant integrated into Microsoft 365 applications like Word, Excel, PowerPoint, Outlook and Teams. Leveraging large language models such as GPT-4o, allows Copilot to draft documents, analyze data, create presentations, and manage emails and meetings. With this new update, Copilot can now create images based on text as well. What can you do with image generation? The integration of OpenAI's latest AI model GPT-4o lets Copilot generate high-quality, photorealistic images from text descriptions, greatly expanding what users can do with visual content. Users can create custom graphics, illustrations and designs without the need for external design tools. Users can modify existing visuals, apply stylistic transformations and produce legible text within images. Microsoft initially began rolling out these GPT-4o image generation tools to enterprise users through Microsoft 365 Copilot last month. The same capabilities are reaching the general public now through the consumer version of Microsoft Copilot. This move puts Microsoft Copilot ahead of the tech company's other creative tools, including Microsoft Designer and Image Creator, both of which rely on older DALL-E models from OpenAI. In contrast, GPT-4o represents the cutting edge in AI-generated imagery, with faster response times and more refined outputs. With these enhancements, Microsoft pushes to position Copilot as a comprehensive AI assistant that competes against the biggest players, OpenAI and Google Gemini.
CNET
23-05-2025
- CNET
This AI Tool Creates Images That Update While You Type. How to Use It
It's easy to feel the overwhelm and oversaturation of the AI landscape. It seems like there's new updates, launches and companies leveraging themselves as the next "big thing" almost every week. And then there's me, someone simply looking for a way to work with an AI tool to generate images in a way that felt somewhat ethical and also a bit more stimulating than typing one prompt and waiting for AI to deliver me something. This is particularly what I enjoyed about Artbreeder, an AI-powered platform that creates and modifies images by blending traits from existing visuals. What is Artbreeder and how does it use AI? Created in 2018 -- and originally named Ganbreeder -- Artbreeder is a platform that uses generative adversarial networks that give you the ability to generate and adjust the image you've created. These "sliders" control attributes of an image, providing you with more contribution to the final image. Artbreeder has four pricing tiers, including a free model and one that's priced up to $31/month. These tiers also range in the amount of credits available each year and paid plans include benefits like faster rendering and downloads, privacy controls and advanced features. Artbreeder's text-to-image feature was added in late 2024, which is an example of how you can crossbreed two or more images while you describe the type of image you'd like to create. Each model within Artbreeder has been trained on a curated dataset, in hopes of creating category or text-specific images. The intended outcome is that you're co-creating the art in real time. (Which I found much more interesting when inputting information.) How to use Artbreeder to create images while you type This is how to use Artbreeder's website for text-to-image creation: Create a free account on Artbreeder. You can also upgrade if you'd like more credits. At the top of the webpage, Artbreeder has three tabs: Create, Community and Browse. Community and Browse will give you access to trending images and recent posts, while Community provides direct access to what other users are whipping up within the platform. In Create, there are various tools, including Animator, AI Director and Composer -- this is located in the upper right hand part of the screen and where you can work with text-to-image generation. You'll see a button up top labeled Description. As you begin typing, the image below will begin to appear, shifting as you edit or add words to your description. I've tried multiple AI text-to-image generators, yet never witnessed the image being created in front of me! You also can upload personal photos to customize or evolve over time using Artbreeder's tools. At the bottom of the screen are multiple buttons with other features, including reading more about Composer, enhancing your image output and downloading an image to your desktop. Once your creation feels complete, you can also share your creations with others under the Community tab. Should you use Artbreeder? Images shift and develop as you continue typing your prompt. Artbreeder / Screenshot by CNET Artbreeder is an easy-to-use AI platform that has myriad features and tools. Its editing gives you more control and flexibility over image output -- and an ability to watch the process along the way. Now, for anyone curious about Artbreeder's ethics, it's important to note that generated images are released under CC0 (Creative Commons Zero) which means that your creations are considered public domain. Also, you can only upload public domain images or images of your own -- but the training of its datasets may contain copyrighted works (Artbreeder didn't immediately respond to a request for comment on this). This goes along with the long-standing debate around infringement vs. fair use. So while its user creation licensing may make it safer for reuse than others, there's still a gray area around content boundaries and image protection. Essentially, Artbreeder is ideal for people in early creative stages, like those developing characters or looking to experiment with concepts quickly and visually. I can also see writers building fictional worlds or students learning about AI art will find it valuable. Yet, professional designers needing more precision than its output and creators concerned about training data ethics may find it too limited or risky. It's a great tool for exploration and inspiration but not always the final destination for high-level work or premium output. But it does provide you with vivid output and keeps other AI tools or ways to experiment with them readily available.
The Verge
20-05-2025
- Business
- The Verge
Google says its new image AI can actually spell
Google is launching a new version of its image generation model, called Imagen 4, and the company says that it offers 'stunning quality' and 'superior typography.' 'Our latest Imagen model combines speed with precision to create stunning images,' Eli Collins, VP of product at Google Deepmind, says in a blog post. 'Imagen 4 has remarkable clarity in fine details like intricate fabrics, water droplets, and animal fur, and excels in both photorealistic and abstract styles.' Sample images from Google do show some impressive, realistic detail, like one showing a whale jumping out of the water and another of a chameleon. The AI model is also 'significantly better at spelling and typography,' which Collins says makes it easier to create greeting cards, posters, and comics. (When OpenAI recently added image generation to ChatGPT, the company also touted its text rendering improvements, but it's still susceptible to typos.) In some images provided by Google, the text does look good — it's perfectly legible in a short comic, for example, and even a tiny font in a mock stamp is readable. But we'll have to see how the model's text rendering capabilities hold up in the hands of regular users. Imagen 4 will be available on May 20th in the Gemini app, Whisk, and Vertex AI, as well as in Slides, Vids, Docs, 'and more in Workspace,' Collins says. Also, Google plans to launch a 'fast variant' of Imagen 4 sometime 'soon,' which it says is 'up to 10x faster than Imagen 3.'
TechCrunch
20-05-2025
- Business
- TechCrunch
Imagen 4 is Google's newest AI image generator
Google is rolling out a new image-generating AI model, Imagen 4, that the company claims delivers higher-quality results than its previous image generator, Imagen 3. Unveiled at Google I/O 2025 on Tuesday, Imagen 4 is capable of rendering 'fine details' like fabrics, water droplets, and animal fur, Google says. The model can handle both photorealistic and abstract styles, creating images in a range of aspect ratios and up to 2K resolution. 'Imagen 4 is [a] huge step forward in quality,' Josh Woodward, who leads Google's Labs group, said during a press briefing. 'We've also [paid] a lot of attention and fixes around how it generates text and topography, so it's wonderful for creating slides or invitations, or any other thing where you might need to blend imagery and text.' A sample from Imagen 4. Image Credits:Google There's no shortage of AI image generators out there, from ChatGPT's viral tool to Midjourney's V7. They're all relatively sophisticated, customizable, and capable of creating high-quality AI artwork. So what makes Imagen 4 stand out from the crowd? Another Imagen 4 sample. Image Credits:Google According to Google, Imagen 4 is fast — faster than Imagen 3. And it'll soon get faster. In the near future, Google plans to release a variant of Imagen 4 that's up to 10x quicker than Imagen 3. Imagen 4 is available as of this morning in the Gemini app, Google's Whisk and Vertex AI platforms, and across Google Slides, Vids, Docs, and more in Google Workspace.
