<p>HiDream-O1-Image (codename Peanut) is an 8B text-to-image foundation model from HiDream.ai, built on a Pixel-level Unified Transformer (UiT) that operates end to end on raw pixels with no external VAE or separate text encoder. The same checkpoint handles text-to-image, instruction-based editing, and multi-reference subject personalization natively at up to 2,048 x 2,048.</p>

<p><strong>Originally released by <a href="https://huggingface.co/HiDream-ai/HiDream-O1-Image" rel="ugc">HiDream.ai</a> on Hugging Face.</strong> All credit for the model goes to the HiDream.ai team. Civitai is hosting a mirror so creators can run it on-site - head to the <a href="https://huggingface.co/HiDream-ai/HiDream-O1-Image" rel="ugc">original repo</a> for weights, updates, the technical report, and to follow the project directly.</p>

<h3>Built by</h3>
<ul>
<li><a href="https://huggingface.co/HiDream-ai" rel="ugc">HiDream.ai</a> - upstream organization and authors of the technical report.</li>
</ul>

<h3><strong>Versions mirrored on Civitai</strong></h3>
<p>Two checkpoints are mirrored, both as fp8 SafeTensors:</p>
<ul>
<li><strong>Standard</strong> - full 50-step model. Best quality. Guidance scale 5.0.</li>
<li><strong>Dev</strong> - distilled 28-step model. Faster, guidance scale 0.</li>
</ul>
<p>HiDream also publishes a 200B+ <strong>Pro</strong> variant upstream, but weights are not public, so it is not mirrored here.</p>

<h3><strong>One model, three tasks</strong></h3>
<p>The same checkpoint handles text-to-image, instruction-based editing with a single reference image, and multi-reference subject-driven personalization with up to ten reference images. Mode is selected by what you pass at inference - no separate adapters or LoRAs needed.</p>

<h3><strong>Native 2K and multilingual text</strong></h3>
<p>Direct synthesis up to 2,048 x 2,048 without upscaling. Strong long-text rendering in both English and Chinese (LongText-Bench 0.979 EN / 0.978 ZH), 0.90 on GenEval for compositional prompts, and 89.83 on DPG-Bench for dense prompt alignment.</p>

<h3><strong>Reasoning-driven prompt agent (upstream only)</strong></h3>
<p>The HiDream repo ships a separate "thinking" prompt agent (Gemma-4-31B or an OpenAI-compatible API) that rewrites raw instructions into self-contained prompts before generation. That agent is not part of the Civitai mirror - if you want it, run upstream locally.</p>

<h3>Links</h3>
<ul>
<li><strong>Hugging Face:</strong> <a href="https://huggingface.co/HiDream-ai/HiDream-O1-Image" rel="ugc">HiDream-ai/HiDream-O1-Image</a></li>
<li><strong>GitHub:</strong> <a href="https://github.com/HiDream-ai/HiDream-O1-Image" rel="ugc">HiDream-ai/HiDream-O1-Image</a></li>
<li><strong>Technical report:</strong> <a href="https://github.com/HiDream-ai/HiDream-O1-Image/blob/main/assets/HiDream-O1-Image.pdf" rel="ugc">PDF</a></li>
<li><strong>License:</strong> MIT</li>
</ul>


Files with SHA256: 7cbf53a475e0a13f92f2ec08bcffdb9b9de4305ef3b6f35cdd784d09dcd8d0cc