Z-Image_clear_anime
- Guide (External site): English | Japanese
- Civitai
- Z-Image_clear_photoreal
- Z-Image-Turbo_clear
- Z-Image_clear_vae
Z-Image_clear_anime is a merged model of Z-Image (Base) and Z-Image-Turbo_clear.
Comparison: Z-Image_clear_anime vs Z-Image-Turbo_clear
Z-Image_clear_anime | Z-Image-Turbo_clear
Z-Image_clear_anime features clearer color expression and sense of depth is better organized.
Which Precision Should I Use?
The order of numerical precision and VRAM usage is FP32 > FP16 > BF16 > FP8. (Note: FP16 and BF16 use the same amount of VRAM.)
Since many LoRAs are released in BF16 format, please select the BF16 format if you prioritize compatibility and training stability.
VAE
For the Z-Image_clear_anime model, we recommend using the custom VAE: Z-Image_natural_vae.
Workflow
This PNG image contains a ComfyUI workflow.
Recommended Settings
- 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
- Color Prompts: English | Japanese
- ComfyUI Color Correction Nodes: English | Japanese
- FP precision: English | Japanese