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 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_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