HiDream-O1-Image is a natively unified image generative foundation model built on a Pixel-level Unified Transformer (UiT) without external VAEs or disjoint text encoders, which natively encodes raw pixels, …

HiDream.ai possesses the only global base model that simultaneously supports four modalities (text, image, video, 3D models), with both proprietary data and model parameters exceeding 13 billion.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

HiDream AI is an advanced AI platform for generating photorealistic images with stunning quality and versatile artistic styles.

HiDream AI is an advanced image generation platform powered by a 17B parameter foundation model. It transforms text descriptions into high-quality, photorealistic images in seconds.

HiDream AI is a free online image generator powered by HiDream-O1 (8B) and HiDream-I1 (17B) open-source models. HiDream-O1 uses a pixel-native Unified Transformer architecture — encoding text, …

Apr 22, 2025 · HiDream another banger after Flux, developed by Vivago AI is making waves and for good reason. It's a powerful, open-source, text-to-image diffusion model with 17 billion parameters, …

May 10, 2025 · HiDream is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within s...

2 days ago · 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 …

May 11, 2026 · The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In this report, we present HiDream …