Reve 2.0 文生图模型发布,在 Artificial Analysis 文生图排行榜上位列第二,仅次于 OpenAI 的 GPT Image 2。该模型将原始文本提示转换为结构化布局提示,生成原生 4K 图像,支持对布局中单个元素进行移动、编辑、替换和重新渲染,同时保留其他元素不变。目前可通过 Reve 应用使用,API 平台即将上线。
Reve 2.0 debuts at #2 on the Artificial Analysis Text to Image Leaderboard, behind only OpenAI's GPT Image 2!
Reve 2.0 is the latest image generation model from Reve. It translates every raw text prompt into a structured layout prompt before generating a native 4K image, making outputs easily editable. Individual elements in the layout can be moved, edited, and swapped, and re-rendered while preserving the rest of the elements.
Reve 2.0 is available now in the Reve app, with access via the Reve API platform coming soon.
Congratulations to @reve on the release!
See below for comparisons between Reve 2.0 and other leading models in the Artificial Analysis Image Arena 🧵