Abiray/HiDream-O1-Image-Dev-FP8

HiDream-O1-Image-Dev (FP8 Scaled)

Repository Notice: This repository hosts the FP8 scaled (hidream_o1_image_dev_fp8_scaled.safetensors) quantized weights of the HiDream-O1-Image-Dev model.

About this variant: The Dev version is a distilled, highly optimized variant of the base 8B model. It dramatically reduces required inference steps from 50 down to 28 steps, offering much faster generation times without sacrificing quality. This standard FP8 quantization further halves the VRAM requirements, making it ideal for rapid inference and high-speed pipelines on a wide range of hardware (such as L40S or mid-range consumer GPUs).

For the official, uncompressed weights and source code, visit the original HiDream-O1-Image-Dev repository.

---

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.

Key Features

• ⚡ Distilled for Speed — The Dev model achieves top-tier quality in only 28 steps (compared to 50 steps for the base model).
• 🧬 Pixel-Level Unified Transformer — One end-to-end model on raw pixels, no VAE, no disjoint text encoder.
• 🎨 One Model, Many Tasks — Text-to-image, long-text rendering, instruction editing, subject-driven personalization, and storyboard generation in a single architecture.
• 🧠 Reasoning-Driven Prompt Agent — Built-in "thinking" agent that resolves implicit knowledge, layout, and text rendering before generation.
• 🖼️ Native High Resolution — Direct synthesis up to 2,048 × 2,048 with sharp fine-grained detail.

Usage & Installation

To use these Dev FP8 weights, you will need the original HiDream inference pipeline.

1. Install the Original Repository

Clone the official repository and install dependencies:

git clone [https://github.com/HiDream-ai/HiDream-O1-Image.git](https://github.com/HiDream-ai/HiDream-O1-Image.git)
cd HiDream-O1-Image
pip install -r requirements.txt