
AWPortrait-Z and Z-Image-Turbo GGUF
Note: All model files and custom nodes below must be downloaded via the client. If you do not have the client, Download >>>
AWPortrait-Z is a portrait-beauty LoRA meticulously built on the Z-Image.
Native-noise reduction: fixed Zimage’s chronic grain—those downy, high-frequency artifacts that plagued skin tones—so complexions now look flawlessly real.
Relit lighting: tamed the base model’s excessive HDR, restoring punchy contrast and saturation; re-engineered artificial-light behavior so studio strobes sit naturally in-scene instead of floating above it.
| Name | Size | Target Dir |
|---|
| z_image_turbo-Q3_K_S.gguf | 3.79 GB | unet |
| z_image_turbo-Q3_K_M.gguf | 4.12 GB | unet |
| z_image_turbo-Q4_K_S.gguf | 4.66 GB | unet |
| z_image_turbo-Q4_K_M.gguf | 4.98 GB | unet |
| z_image_turbo-Q5_K_S.gguf | 5.19 GB | unet |
| z_image_turbo-Q5_K_M.gguf | 5.52 GB | unet |
| z_image_turbo-Q6_K.gguf | 5.91 GB | unet |
| z_image_turbo-Q8_0.gguf | 7.22 GB | unet |
| Name | Size | Target Dir |
|---|
| ae.safetensors | 335 MB | vae |
| Name | Size | Target Dir |
|---|
| Qwen3-4B-Q4_K_M.gguf | 2.50 GB | text_encoders |
| Qwen3-4B-Q5_0.gguf | 2.82 GB | text_encoders |
| Qwen3-4B-Q5_K_M.gguf | 2.89 GB | text_encoders |
| Qwen3-4B-Q6_K.gguf | 3.31 GB | text_encoders |
| Qwen3-4B-Q8_0.gguf | 4.28 GB | text_encoders |
| Name | Size | Target Dir |
|---|
| AWPortrait-Z.safetensors | 680.33 MB | loras |