Z-Image_clear_photoreal

Z-Image_clear_photoreal

• Guide (External site): English | Japanese
• Civitai
• Z-Image_clear_anime
• Z-Image_Turbo_clear
• Z-Image_clear_vae

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Z-Image_clear_photoreal_cover_image_1.png" alt="Z-Image_clear_photoreal_cover_image_1" width="400" height="400"> </div> <div> <img src="./images/Z-Image_clear_photoreal_cover_image_2.png" alt="Z-Image_clear_photoreal_cover_image_1" width="400" height="400"> </div> </div>

Z-Image_clear_photoreal is a high-quality photorealistic image generation model that balances the speed of Z-Image-Turbo_clear with enhanced realism and diversity.

Comparison: Z-Image_clear_photoreal vs Z-Image-Turbo_clear

<div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Z-Image_clear_photoreal_compare_1.png" alt="Z-Image_clear_photoreal_compare_1" width="400" height="400"> </div> <div> <img src="./images/Z-Image-Turbo_clear_compare_1.png" alt="Z-Image-Turbo_clear_compare_1" width="400" height="400"> </div> </div> <p style="text-align:center;">Z-Image_clear_photoreal | Z-Image-Turbo_clear (distilled)</p> <div style="display: flex; justify-content: center; align-items: center; gap: 2em;"> <div> <img src="./images/Z-Image_clear_photoreal_compare_2.png" alt="Z-Image_clear_photoreal_compare_2" width="400" height="400"> </div> <div> <img src="./images/Z-Image-Turbo_clear_compare_2.png" alt="Z-Image-Turbo_clear_compare_2" width="400" height="400"> </div> </div> <div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 90%;"> <img src="./images/Z-Image_clear_photoreal_vs_Z-Image-Turbo_clear_compare2_close_up.png" alt="Z-Image_clear_photoreal_vs_Z-Image-Turbo_clear_compare2_close_up" width="800" height="400"> </div>

Z-Image_clear_photoreal is a merged model of Z-Image-Turbo_clear and Z-Image (Base).

It maintains the high speed and stability of Z-Image-Turbo_clear while significantly improving image quality and diversity.

Image diversity

Z-Image_clear_photoreal

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 60%;"> <img src="./images/Z-Image_clear_photoreal_8images_no1.png" alt="Z-Image_clear_photoreal_8images_no1" width="800" height="800"> </div> <div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 60%;"> <img src="./images/Z-Image_clear_photoreal_8images_no2.png" alt="Z-Image_clear_photoreal_8images_no2" width="800" height="800"> </div>

Z-Image-Turbo_clear (distilled)

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 60%;"> <img src="./images/Z-Image-Turbo_clear_photoreal_8images_no1.png" alt="Z-Image-Turbo_clear_photoreal_8images_no1" width="800" height="800"> </div> <div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 60%;"> <img src="./images/Z-Image-Turbo_clear_photoreal_8images_no2.png" alt="Z-Image-Turbo_clear_photoreal_8images_no2" width="800" height="800"> </div>

Z-Image_clear_photoreal offers better diversity in faces and compositions compared to Z-Image-Turbo_clear (distilled).

---

Model Formats and Image Quality

Generally, the image quality ranks in the following order:

FP32 > FP16 ≒ BF16 > INT8_ConvRot_HQ > MXFP8 > FP8_svd_scaled > FP8

• FP32 is mainly recommended for training purposes.
• FP16 / BF16 can generate high-quality illustrations.
• INT8_ConvRot_HQ offers an excellent balance of speed and quality while using roughly half the VRAM of FP16 / BF16.
• MXFP8, FP8_svd_scaled, and FP8 are currently not recommended, as they are inferior to INT8_ConvRot_HQ in both speed and image quality.

For a detailed comparison of each format, please refer to this page.

---

VAE

For the Z-Image_clear_photoreal model, we recommend using the custom VAE: Z-Image_clear_vae.

• Z-Image_natural_vae: lower saturation, more natural look
• Z-Image_clear_vae: higher saturation, vivid and vibrant look

We provide several color-style variations, so feel free to choose the one that matches your preference.

---

Workflow

<div style="text-align: center; margin-left: auto; margin-right: auto; width: 800px; max-width: 100%;">   <img src="./images/Z-Image_clear_photoreal_20260206.png" alt="Z-Image_clear_photoreal_workflow" width="1200" height="600"> </div>

This PNG image contains an embedded ComfyUI workflow.

---

Recommended Settings

• Sampler: euler
• Scheduler: beta
• Steps: 12 (6-18)
• ModelSamplingAuraFlow: shift 6 (3-9)
• CFG scale: 1

Note: Negative Prompts have no effect.

---

Upscaler

your choice, examples:

• 4x-SwinIR-L_GAN
• 4x_NMKD-Superscale-SP_178000_G

---

Tips (External Sites)

• Z-Image-Turbo_clear: English | Japanese
• FP / BF / Int8_ConvRot Format Image Quality and Generation Time: English | Japanese
• FP precision: English | Japanese
• About VAE: English | Japanese

---

License

• Apache-2.0