HiDream 用 8B 参数挑战了传统扩散架构的统治地位，做图像生成或研究的开发者值得关注——它可能改变你对模型效率与架构的认知。
HiDream 开源了 8B 参数的图像模型 HiDream-O1-Image，声称性能与 27B 的 Qwen-Image 等更大模型持平。该模型采用像素级统一 Transformer，无需 VAE 和文本编码器，直接在原始像素上端到端处理。它支持文生图、长文本渲染、指令编辑、主体个性化及故事板生成等多种任务。内置推理驱动的提示代理，能先理解用户意图再生成，在长文本渲染基准上接近 200B+ 模型的表现。这暗示传统扩散管线可能不再是唯一的主流路径。
HiDream just open-sourced an 8B image model with a…
HiDream just open-sourced an 8B image model with a big message behind it: the old diffusion pipeline (VAE-plus-text-encoder) may not be the only serious path left.
8B param, HiDream-O1-Image (8B) claims parity with models over 3x its size (e.g., 27B Qwen-Image).
@HiDream_AI , @vivago_ai
Key Features
🧬 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.
⚡ Exceptional Efficiency and Versatility at 8B Scale — With only 8B parameters, achieves performance parity with or even surpasses larger open-source DiTs and leading closed-source models.
Most image models still split the job across a text encoder, a VAE, and a diffusion model, so details can get lost when real pixels are compressed into hidden image codes.
HiDream-O1-Image removes that split by using a Pixel-level Unified Transformer, where raw image patches, text tokens, and task conditions enter the same model space.
That means text-to-image, image editing, and subject personalization become variants of one in-context generation task, not separate pipelines.
A prompt agent first rewrites messy user requests into clearer visual instructions, reasoning through layout, subject attributes, physics, and context before generation.
The strongest result is text rendering.
On LongText-Bench, the 8B model scores 0.979 in English and 0.978 in Chinese, while the 200B+ model reaches 0.982 and 0.980.
That is the part to watch, because clean text inside generated images is still one of the hardest problems for image models.
🧵 1.