最近一段时间，文本转图像模型 Stable Diffusion 可谓是爆红 AI 圈，其是由慕尼黑大学和 Runway 的研究者基于 CVPR 2022 的论文《High-Resolution Image Synthesis ...

Keras is a deep learning API written in Python that runs on the machine learning platform TensorFlow. It is reported that Stable Diffusion of image generation AI will be about 30% faster by using ...

On Thursday, Stability AI announced Stable Diffusion 3, an open-weights next-generation image-synthesis model. It follows its predecessors by reportedly generating detailed, multi-subject images ...

The new Stable Diffusion 3.0 model aims to provide improved image quality and better performance in generating images from multi-subject prompts.

OpenAI may have a successor to today's image generators with "consistency models," which trade quality for speed but have room to grow.

Stability AI introduced innovations into the new Stable Diffusion model, SDXL 1.0, that make fine-tuning easier and improve composition.

On Tuesday, Stability AI launched Stable Diffusion XL Turbo, an AI image-synthesis model that can rapidly generate imagery based on a written prompt.

DeepSeek's new open-source AI model surpassed Stability AI and Microsoft-backed OpenAI's models in benchmarks for image generation, the Chinese startup said in a technical report on Monday.