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).
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 lookZ-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)
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
