Home Search
diffusion - search results
If you're not happy with the results, please do another search
New Stable Diffusion 3.5 AI Image Generation Models Promise Speed and Flexibility
Stability AI´s new Stable Diffusion 3.5 models bring customizable image generation, with faster performance and improved prompt adherence.
Stability AI Introduces Resource-Efficient Stable Diffusion 3 Medium
Stability AI has announced out its latest AI model, Stable Diffusion 3 Medium, which aims to operate efficiently on consumer-level GPUs. This iteration promises...
Stable Diffusion 3 Public Preview Begins June 12, Stability AI Announces
Stability AI has announced the public preview of its next text-to-image model, Stable Diffusion 3, starting June 12. The reveal occurred during Computex 2024...
Stable Diffusion Models Now Accessible Through Paid Membership Model
Stability AI charges for commercial AI use with tiered subscriptions starting at $20/month. Free tier for personal/research.
Stability AI Enters Video Generation Arena with Stable Video Diffusion Release
Stability AI introduces two AI models, Stable Video Diffusion and SVD-XT, that generate short videos from static images.
Stability AI Unveils Advanced 3D Modeling and Enhanced Image Tools for Stable Diffusion
Stability AI has announced major improvements to Stable Diffusion, including better 3D modelling capabilities and image enhancing tools.
Generative AI: Poisson Flow Generative Models Beat Diffusion Models for Image Creation by Factor...
Poisson Flow Generative Model (PFGM) highlights how physics-inspired AI can transform generative AI.
Stability AI and Nvidia to Enhance Stable Diffusion XL Performance
Central to this performance boost is the integration of Nvidia's TensorRT, a high-performance optimization framework.
Alibaba Launches AI Image Generator Similar to DALL-E, Midjourney, Stable Diffusion
Tongyi Wanxiang uses a generative AI model that responds to text prompts in both Chinese and English to generate detailed images.
Stable Diffusion XL 1.0: A New Diffusion Model for Generating High-Quality Images
Stable Diffusion XL 1.0 is a new diffusion model that is more stable and efficient, available for testing in the Stable Diffusion Discord.
Copyright Lawsuit against Diffusion and Midjounrey Led by Same Team Battling GitHub Copilot
A lawsuit similar to the case against GitHub Copilot alleges AI art generators are infringing the copyright of billions of people.
TSMC Faces U.S. Scrutiny Over Huawei Chip Purchase, Risking $1 Billion Fine
The U.S. has moved closer to penalizing TSMC with a fine exceeding $1B for a chip order allegedly linked to blacklisted Chinese tech giant Huawei.
OpenAI Is Testing Watermarks for Its GPT-4o Image Generation Mode
OpenAI is testing a visible watermark for mages created with ChatGPT-4o i as part of its broader efforts to improve AI content traceability and policy compliance.
Meta’s MoCha AI Animates Characters From Just Voice and Text
Meta has introduced MoCha, an AI system that generates full-body character videos from just voice and text, with no need for reference footage.
New AI Model Forecasts Wildfire Activity by Tracking Fuel, Not Just Fire Risk
ECMWF has developed an AI model that forecasts actual wildfire activity using data on vegetation, weather, and ignition sources.
Runway’s Gen-4 Ups the Stakes in AI Video Generation With Powerful Cinematic Controls
Runway has upgraded its AI video tools with Gen‑4, combining cinematic controls, scene-level prompting, and detailed camera path customization.
U.S. Expands China AI Chip Export Ban Once Again
The U.S. has expanded AI chip export bans on China, tightening restrictions on Nvidia and ASML while pushing allies to enforce stricter semiconductor controls.
OpenAI Adds GPT-4o Image Generation Mode With Interactive Editing
OpenAI has added GPT-4o image generation to ChatGPT, allowing users to create, edit, and refine AI-generated images directly within the chat interface.
Stability AI’s New Stable Virtual Camera Converts 2D Images into 3D Videos
Stability AI has launched Stable Virtual Camera, an AI model that converts still images into immersive 3D videos with realistic depth and perspective.
Meta Makes Passthrough API for Quest Available For Experimental MR Development
Meta has opened its Passthrough Camera API for Quest headsets, enabling developers to experiment with immersive mixed reality projects.
