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 🧵

Ever wanted to generate images from text but also refine them with your own edits? Meet HiDream O1 Image Dev, a model that takes image-text-to-image to a new level. It's like having a creative partner that understands both your words and your visual tweaks.

HiDream-O1-Image-Dev-2604 debuts as the leading open weights Text to Image model in the Artificial Analysis Image Arena, with the base HiDream-O1-Image and HiDream-O1-Image-Dev also available open weights but landing lower on the leaderboard @HiDream_AI's O1-Image family spans three models: the 8B HiDream-O1-Image, its distilled HiDream-O1-Image-Dev, and HiDream-O1-Image-Dev-2604, a fine-tune of Dev with a prompt-enhancement pipeline, previously listed pseudonymously as Peanut. The base and Dev models accept text plus up to 10 image inputs, spanning generation and instruction-based image editing. On the Artificial Analysis Text to Image Arena, HiDream-O1-Image-Dev-2604 leads all open weights models, delivering quality similar to proprietary models like ByteDance's Seedream 4.0 and Black Forest Labs' FLUX.2 [max]. In Image Editing, HiDream-O1-Image is the second-highest open weights model, behind only Tencent's HunyuanImage 3.0 Instruct. Weights and the full inference pipeline (including HiDream's prompt refiner used during evaluation for HiDream-O1-Image-Dev-2604) are open-source on Hugging Face and GitHub under the MIT license. HiDream-O1-Image and HiDream-O1-Image-Dev are also available across third-party API providers including Fal, priced on Fal at $10/1k images and $5/1k images respectively. Congratulations to @HiDream_ai on the releases! See below for comparisons between the HiDream-O1-Image family and other leading models in the Artificial Analysis Image Arena 🧵