<h1 id="z-image_clear_photoreal">Z-Image_clear_photoreal</h1><ul><li>Guide (External Site): <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2026/02/z-image-clear-photoreal.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/nf3b7305aad22">Japanese</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/easygoing0114/Z-Image_clear_photoreal">Hugging Face</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2197598/z-image-turboclear">Z-Image-Turbo_clear</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2191617">Z-Image_clear_vae</a></li></ul><h2 id="compare-to-z-image-turbo_clear-(distilled)">Compare to Z-Image-Turbo_clear (distilled)</h2><span style="background-color:rgb(11, 15, 25);color:rgb(179, 188, 201);font-family:&quot;Source Sans Pro&quot;, ui-sans-serif, system-ui, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;, &quot;Noto Color Emoji&quot;;font-size:16.8px">Z-Image_clear_photoreal | Z-Image-Turbo_clear (distilled)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/91d85f00-068e-4d3a-9daa-98897eea6d5e/original=true/91d85f00-068e-4d3a-9daa-98897eea6d5e.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1ecd9125-5c5e-4ddd-b795-3cbc7c41ba24/original=true/1ecd9125-5c5e-4ddd-b795-3cbc7c41ba24.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/fce4907f-1b3b-4907-a40a-a1312132b95e/original=true/fce4907f-1b3b-4907-a40a-a1312132b95e.jpeg" />Z-Image_clear_photoreal is a merged model of <a target="_blank" rel="ugc" href="https://civarchive.com/models/2197598/z-image-turboclear">Z-Image-Turbo_clear</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/Tongyi-MAI/Z-Image">Z-Image (Base)</a>.It maintains the high speed and stability of Z-Image-Turbo_clear while significantly improving image quality and diversity.<h2 id="image-diversity">Image diversity</h2><h3 id="z-image_clear_photoreal">Z-Image_clear_photoreal</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ed62492e-a7e7-4b80-9085-f3d9fbb5d5da/original=true/ed62492e-a7e7-4b80-9085-f3d9fbb5d5da.jpeg" />Z-Image_clear_photoreal produces rich variation in faces and compositions.<h3 id="z-image-turbo_clear-(distilled)">Z-Image-Turbo_clear (distilled)</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/dbdd5361-71c2-4212-96a8-70b00bff5739/original=true/dbdd5361-71c2-4212-96a8-70b00bff5739.jpeg" />Z-Image-Turbo_clear (distilled) tends to generate very similar-looking images with little diversity.<hr /><h2 id="model-formats-and-image-quality">Model Formats and Image Quality</h2>Generally, the image quality ranks in the following order:FP32 &gt; FP16 ≒ BF16 &gt; INT8_ConvRot_HQ &gt; MXFP8 &gt; FP8_svd_scaled &gt; FP8<ul><li>FP32 is mainly recommended for training purposes.</li><li>FP16 / BF16 can generate high-quality illustrations.</li><li>INT8_ConvRot_HQ offers an excellent balance of speed and quality while using roughly half the VRAM of FP16 / BF16.</li><li>MXFP8, FP8_svd_scaled, and FP8 are currently not recommended, as they are inferior to INT8_ConvRot_HQ in both speed and image quality.</li></ul>For a detailed comparison of each format, please refer to <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2026/06/floating-point-precision-speed.html">this page</a>.<hr /><h2 id="vae">VAE</h2>For the Z-Image_clear_photoreal model, we recommend using <a target="_blank" rel="ugc" href="https://civarchive.com/models/2191617">Z-Image_clear_vae.</a><ul><li>Z-Image_natural_vae: lower saturation, more natural look</li><li>Z-Image_clear_vae: higher saturation, vivid and vibrant look</li></ul>We provide several color-style variations, so feel free to choose the one that matches your preference.<hr /><h2 id="workflow">Workflow</h2>The <a target="_blank" rel="ugc" href="https://huggingface.co/easygoing0114/Z-Image_clear_photoreal#workflow">PNG workflow</a> can be downloaded from <a target="_blank" rel="ugc" href="https://huggingface.co/easygoing0114/Z-Image_clear_photoreal">Hugging Face.</a><hr /><h2 id="recommended-settings">Recommended Settings</h2><h3 id="general">General</h3><ul><li>Sampler: euler</li><li>Scheduler: beta</li><li>Steps: 12 (6-18)</li><li>ModelSamplingAuraFlow: shift 6 (3-9)</li><li>CFG scale: 1</li></ul>Note: Negative Prompts have no effect.<h3 id="upscaler">Upscaler</h3>your choice, examples:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/easygoing0114/AI_upscalers/tree/main">4x-SwinIR-L_GAN</a></li><li><a target="_blank" rel="ugc" href="https://openmodeldb.info/models/4x-NMKD-Superscale">4x_NMKD-Superscale-SP_178000_G</a></li></ul><hr /><h2 id="tips-(external-sites)">Tips (External Sites)</h2><ul><li>Z-Image-Turbo_clear: <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2025/12/z-image-turbo-clear.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/nd1323246e146">Japanese</a></li><li>FP / BF Format Image Quality and Generation Time: <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2026/06/floating-point-precision-speed.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n99d0ed2f1c1d">Japanese</a></li><li>ComfyUI Color Correction Nodes: <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2025/09/comfyui-easygoing-nodes.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n5bb33311b866">Japanese</a></li><li>FP precision: <a target="_blank" rel="ugc" href="https://www.ai-image-journey.com/2025/01/flux1-compression-formats.html">English</a> | <a target="_blank" rel="ugc" href="https://note.com/ai_image_journey/n/n3903415a5a33">Japanese</a></li></ul><hr /><h2 id="license">License</h2><ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/easygoing0114/Z-Image_clear_photoreal/blob/main/LICENSE">Apache-2.0</a></li></ul>

Z-Image_clear_photoreal

zImageClearPhotoreal_int8ConvrotHQ.safetensors

INT8_ConvRot_HQ

Files with SHA256: 435e5a640a8f1a9cccb2ddacacd6fa7b62d28292f74162907fe8c08ab2dac845