HiDream O1 Image 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, text, and task specific conditions in a single shared token space — supporting text to image, image editing, and subject driven personalization at up to 2,048 × 2,048. Project Updates 💬 June 22, 2026: Join our Discord community for questions, support, and discussions. 🚀 May 14, 2026: We open sourced HiDream O1 Image Dev 2604 with its prompt refiner, tailored for text to image generation task. 🛠️ May 13, 2026: Inference & pipeline updates — accelerated IP inference; the IP pipeline now supports layout and skeleton conditioning; updated the Dev editing scheduler. For editing tasks we recommend using the full model. PyTorch 2.9.x is not recommended due to the issue. 🤗 May 10, 2026: Try HiDream O1 Image online on Hugging Face Spaces — 🤗 HiDream O1 Image and 🤗 HiDream O1 Image Dev. 📕 May 10, 2026: Our technical report is now available — 📑 HiDream O1 Image.pdf. 🚀 May 8, 2026: We've open sourced HiDream O1 Image (8B) , including both the undistilled and distill…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy