HiDream 用统一 Transformer 架构简化了文生图流程，做图像生成或模型对比的开发者值得关注其性价比和效果。
HiDream 发布 O1-Image-1.5 模型，在 Artificial Analysis 文生图排行榜上位列第三，超越 Google 的 Nano Banana 2。该模型基于统一 Transformer（UiT）架构，将像素、文本和任务条件编码到同一共享 token 空间，无需分离文本编码器、VAE 和图像模型。它支持生成 2K 分辨率图像，质量接近 OpenAI 的 GPT Image 1.5 和 Gemini 3.1 Flash Image Preview。定价为每千张图像 80 美元，目前在 HiHarness 和 Vivago 平台可用。
HiDream-O1-Image-1.5 lands at #3 on the Artificial…
HiDream-O1-Image-1.5 lands at #3 on the Artificial Analysis Text to Image Leaderboard, surpassing Google’s Nano Banana 2!
HiDream’s latest addition to the O1 Image model series is a closed-source model capable of generating images up to 2K resolution from text prompts. The O1 Image family is built on HiDream's Unified Transformer (UiT), which encodes raw pixels, text, and task conditions in a single shared token space rather than splitting the task across a separate text encoder, a VAE, and an image model.
On the Artificial Analysis Text to Image Arena, HiDream-O1-Image-1.5 places second only to OpenAI’s image models, delivering quality similar to GPT Image 1.5 (high), Nano Banana 2 (Gemini 3.1 Flash Image Preview), and Cosmos3-Super-Text2Image.
HiDream-O1-Image-1.5 is priced at $80/1k images and is currently available on HiDream’s HiHarness platform (accessible via their website), as well as on the Vivago platform.
Congratulations to @HiDream_ai and @vivago_ai on the release!
See below for comparisons between HiDream-O1-Image-1.5 and other leading models in the Artificial Analysis Image Arena 🧵