Z-Image_clear_anime

• Guide (External site): English | Japanese

• Hugging Face

• Z-Image_clear_photoreal

• Z-Image_Turbo_clear

• Z-Image_clear_vae

Comparison: Z-Image_clear_anime vs Z-Image-Turbo_clear

Z-Image_clear_photoreal | Z-Image-Turbo_clear

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

It features clearer color expression and sense of depth is better organized.

Model Format and Quality

Generally, model size and image quality are proportional.

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

Generation time varies greatly depending on whether the model can be loaded into VRAM, and the supported formats are determined by the GPU generation.

MXFP8 is the latest standard designed for the RTX 5000 series. On unsupported GPUs, however, fallback mechanisms will actually slow down processing, so their use is not highly recommended.

For a comparison of image quality and generation time by format, please see this page.

If you are unsure which precision to use, it is safest to choose the BF16 format.

VAE

For the Z-Image_clear_anime model, we recommend using the custom VAE: Z-Image_natural_vae.

Workflow

The PNG workflow can be downloaded from Hugging Face.

Recommended Settings

General

• Sampler: euler

• Scheduler: beta

• Steps: 12 (Range: 6-18)

• ModelSamplingAuraFlow: shift 6 (Range: 3-9)

• CFG scale: 1

Note: Negative Prompts have no effect.

Upscaler

your choice, examples:

• RealESRGAN_x4Plus Anime 6B (Commercial use)

• IllustrationJaNai_V1_ESRGAN (Non-Commercial use)

Tips (External Sites)

• Z-Image-Turbo_clear: English | Japanese

• FP / BF Format Image Quality and Generation Time: English | Japanese

• ComfyUI Color Correction Nodes: English | Japanese

• FP precision: English | Japanese

License

• Apache-2.0