Z-Image_clear_photoreal

Z-Image_clear_photoreal_cover_image_1
Z-Image_clear_photoreal_cover_image_1

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

Z-Image_clear_photoreal_compare_1
Z-Image-Turbo_clear_compare_1

Z-Image_clear_photoreal | Z-Image-Turbo_clear (distilled)

Z-Image_clear_photoreal_compare_2
Z-Image-Turbo_clear_compare_2
Z-Image_clear_photoreal_vs_Z-Image-Turbo_clear_compare2_close_up

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

Z-Image_clear_photoreal_8images_no1
Z-Image_clear_photoreal_8images_no2

Z-Image-Turbo_clear (distilled)

Z-Image-Turbo_clear_photoreal_8images_no1
Z-Image-Turbo_clear_photoreal_8images_no2

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


Which Precision Should I Use?

FP_compare1
FP_compare2

FP8 format shows noticeable degradation even to the naked eye.

FP32_vs_BF16_difference

Note: Image Difference Check Tool

Among the rest, the order of precision is FP32 > FP16 > BF16, but it is difficult to distinguish them with the naked eye.

Since many LoRAs are released in BF16 format, please select the BF16 format if you prioritize compatibility.


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

  Z-Image_clear_photoreal_workflow

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:


Tips (External Sites)


License

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support