AI image generation

Google introduces an experimental AI world model that instantly generates and explores interactive 3D virtual worlds via text or images, geared toward creative, gaming and research scenarios.

Google launched a new generation of free high-speed image generation model, supporting high-fidelity output, fast editing, subject consistency maintenance and real-time information fusion, suitable for content creation, advertising and marketing, design and art, and other multi-scenarios of efficient creation.

NVIDIA's revolutionary 3D scene generation system supports free roaming and interactive exploration, providing an efficient and realistic solution for building virtual environments in multiple fields.

OpenAI's next-generation AI image generation engine realizes high-quality, multi-image consistent, commercial-ready visual content production through “think-aloud” generation.

The high-precision 3D generation of large models launched by ByteDance supports the generation of interactive 3D assets from a single image/text through geometric structure reduction and physically realistic material generation technology, which is widely used in industrial manufacturing, embodied intelligence and digital twins.

An AI generation tool based on node-based workflows, which enables creators to precisely control the generation process of images, videos, and audios through modularization and visualization, achieving professional-grade content production from “random generation” to “stable reproduction”. The program is designed to provide creators with precise control over the image, video, and audio generation process.

Free online multifunctional AI creation platform, integrating avatar generation, resume optimization, video effects, academic assistance and other functions, without registration to use.

Amap has launched the world’s first native 3D city world model. By inputting satellite imagery or text, it can generate a kilometer-scale 3D city on a consumer-grade graphics card in just 10 minutes—ready for direct import into game engines.

Launched by Alibaba, this third-generation image-generation model supports ultra-long 4.5k inputs and 10px-precise text rendering. It emphasizes “rich content, authentic details, and deep knowledge” and serves as a practical productivity tool.

Black Forest Labs' lightweight, open-weight image model supports text-to-image generation, editing with multiple reference images, and layout control, and offers both an API and a self-hosting option.

An online platform that combines AI-powered conversation, image generation and editing, and video and music creation.

PixAI is an AI-powered platform for anime and illustration creation that supports text-to-image generation, reference image editing, partial redrawing, and LoRA. It is ideal for character design and illustration iteration, and offers both free credits and paid membership options.