Stability AI has once again broken through technical barriers by launching the new Stable Diffusion 3.5 Medium model. This AI art tool aimed at the general public is not only completely free for commercial use but also achieves a perfect balance between high performance and accessibility. With its multimodal diffusion transformer (MMDiT-X) architecture and a streamlined design of 2.5 billion parameters, this model cleverly addresses the hardware threshold for ordinary users, requiring only 9.9GB of VRAM to run smoothly on most consumer-grade graphics cards.

Recently, a research team from the Beijing Academy of Artificial Intelligence launched a new image generation model called OmniGen. Unlike previous tools such as Stable Diffusion, which focused on a single task, OmniGen's biggest highlight is its multi-capability: it can handle a variety of image generation tasks within a unified framework, including text-to-image generation and image editing, making it a versatile player. This means that users only need to provide simple prompts.

Google's DeepMind, in collaboration with the Massachusetts Institute of Technology (MIT), recently announced a significant research breakthrough. The research team developed a new autoregressive model called 'Fluid', which has made groundbreaking progress in the field of text-to-image generation. After scaling up to 10.5 billion parameters, the model has demonstrated outstanding performance. This research overturns the industry's common perception; while autoregressive models have dominated the language processing domain, they have traditionally been seen as inferior to Stable Diffusion and Goog.

Last night, Stability AI unveiled its most powerful model - Stable Diffusion 3.5, which is not just a single model, but a package containing three versions, designed to meet the diverse needs of researchers, business enthusiasts, startups, and enterprises. The three versions are Stable Diffusion 3.5 Large, Stable Diffusion 3.5 Large Turbo, and one that will be available on October 29.

A recent study proposed a new method that leverages human attention to enhance the quality of AI-generated images. This method uses a saliency detector to identify the most important areas in the image and prioritizes the generation of these areas. Traditional image generation methods optimize the entire image uniformly, whereas the new method identifies and prioritizes more 'important' regions, similar to human attention. This approach can improve image quality and fidelity to textual prompts. Researchers utilized stable diffusion models and saliency detectors to generate images, and

A startup team from Mexico City, 'Somewhere Someone', successfully attracted collaboration from Adidas by designing a football team jersey using artificial intelligence, showcasing the integration of technological innovation and traditional craftsmanship. The team created innovative product concept images through AI image generation technology, particularly incorporating traditional Mexican embroidery elements into the design of the Adidas-styled national team jersey, capturing global attention. This design not only enhances the unique appeal of the product but also provides economic independence opportunities for over 3,000 artisans, potentially impacting 15,000 people. Adidas' involvement not only promotes...

The German research institution LAION has created and released a new dataset, Re-LAION-5B, claiming to have removed links to suspected Child Sexual Abuse Material (CSAM). This dataset is a revised version of the old LAION-5B dataset, incorporating recommendations from the Internet Observation Foundation, Human Rights Watch, the Canadian Centre for Child Protection, and Stanford Internet Observatory. Re-LAION-5B is divided into two versions: Research and Research-Safe, with the latter additionally removing NSFW content. The dataset aims to support

Runway secretly removed the codebase of Stable Diffusion v1.5 from the Hugging Face platform, sparking significant concern in the tech community. This action was taken without notifying Hugging Face or community members, leaving developers and researchers dependent on these resources in a difficult position. Stable Diffusion v1.5 was a key part of a research project involving Runway, but was ultimately taken down due to copyright issues. Runway's....

ViPer is a personalized image generation tool designed to interact with users to learn and apply their artistic preferences, similar to Midjourney. By analyzing user feedback on images, ViPer identifies preferences such as 'soft colors', 'diffused lighting', and 'dreamy atmosphere' and uses these as guiding principles when generating new images, avoiding elements that the user dislikes. This allows ViPer to create images that align with the user's aesthetic and reflect a personalized style, providing a unique artistic creation experience. The online experience can be found at: h

Researchers from Stanford University and the University of California, Berkeley conducted an experiment to explore the consequences of retraining AI image generation models using images generated by the AI itself. The experiment utilized the Stable Diffusion (SD) model and selected high-quality facial images from the FFHQ dataset for automatic generation. The results showed that after retraining, the AI model produced highly distorted images. This distortion originated not only from the text prompts used for retraining but also persisted even when retraining was done solely with real images.

The core research team of Stable Diffusion has announced their collective resignation, attracting widespread attention in the tech community. With team leaders and authors leaving, Stability AI may face challenges due to financial difficulties. The Stable Diffusion project was jointly developed by the University of Munich and an AI startup. Stability AI has high operating costs and increasing financial pressure, with rumors of a potential sale. Following the release of Stable Diffusion 3, the mass resignation of the core team raises doubts about the company's future.

The Stable Diffusion 3 model introduces the DiT (Diffusion Transformer) architecture, which significantly improves quality. Stable Diffusion 3 outperforms other text-to-image generation systems. The parameter count of Stable Diffusion 3 ranges from 800M to 8B. The SD3 architecture is developed in collaboration with core members of Sora and an assistant professor from New York University.

The technical report on Stable Diffusion 3 reveals that SD3 adopts the Multimodal Diffusion Transformer architecture MMDiT. SD3 introduces reweighted flow technology to enhance performance. The report discusses the scaling research of SD3 and anticipates future performance improvements along with issues and suggestions regarding the text encoder.

Stable Diffusion 3 is the most powerful text-to-image model. It adopts the MMDiT architecture, demonstrating performance that surpasses existing text-to-image generation systems. Stable Diffusion 3 excels in visual aesthetics, text adherence, and layout compared to other advanced models. The MMDiT architecture combines DiT and rectangular flow forms, processing image and language representations through independent weight sets. Stable Diffusion 3 offers flexibility.

This article reports on the situation where artist Greg Rutkowski requested the removal of his artworks from AI, yet a Rutkowski-specific image generator was created.