image-generation

Stability AI and NVIDIA have launched Stable Diffusion 3.5 NIM, a microservice designed to accelerate image generation performance and simplify enterprise deployment. The collaboration packages Stable Diffusion 3.5 as an NVIDIA NIM (NVIDIA Inference Microservice) for optimized inference.

Stability AI has released TensorRT-optimized versions of the Stable Diffusion 3.5 model family in collaboration with NVIDIA. The optimization uses FP8 quantization to achieve 2x faster generation speed and 40% lower VRAM requirements on supported RTX GPUs.

Stability AI has released ONNX-optimized versions of Stable Diffusion engineered to run faster and more efficiently on AMD Radeon GPUs and Ryzen AI APUs. The collaboration with AMD targets broader hardware compatibility for the image generation model.

Stability AI's Stable Diffusion 3.5 Large model is now available through Microsoft Azure AI Foundry, giving businesses integrated access to professional-grade image generation within Azure's ecosystem. The deployment expands SD3.5 Large's availability across major cloud platforms.

Adobe is rolling out custom models for Firefly, allowing creators to train the generative model on 10-30 of their own images to generate new content matching their specific visual style. The feature costs 500 credits per training session and supports three methods: photography style, illustration style, and character consistency.

Microsoft's superintelligence team, led by Mustafa Suleyman, has released MAI-Image-2, a text-to-image generator that currently ranks third on the Arena.ai leaderboard for text-to-image models, behind OpenAI's GPT-Image-1.5 and Google's Nano Banana 2. The model is now available for testing in the MAI Playground and will roll out to Copilot and Bing Image Creator, with API access opening to all developers through Microsoft Foundry.

Midjourney has released an early version of V8 for community testing, achieving roughly 5x faster image generation and introducing native 2K resolution via --hd mode. However, premium features including --hd, --q 4, style references, and mood boards cost four times as much as standard generation, with Relax mode unavailable at launch.

Google DeepMind has released Nano Banana 2, an image generation model that combines advanced world knowledge and subject consistency with faster inference speeds comparable to its Flash offering. The model is positioned as production-ready with capabilities previously associated with Pro-tier performance.

Google has relaunched its Flow AI creative studio as a unified platform for image and video creation. The updated tool includes free image generation capabilities and new editing features designed to streamline creative workflows.

Segmind has released SegMoE, a mixture-of-experts (MoE) diffusion model designed to accelerate image generation while reducing computational overhead. The model applies MoE techniques traditionally used in large language models to the diffusion model architecture, enabling selective expert activation during inference.