Pornmaster Z-Image Turbo T2I Workflow-Double checkpoints & realism enhancer

詳細

ファイルをダウンロード (1)

モデル説明

PornMaster-色情大师 Z-image

Pornmaster Z Image Turbo Workflow

Pornmaster Z Image Turbo Controlnet Workflow

PornMaster Z-image-turbo Controlnet: Cosplay - Anime to Realistic Style

PornMaster Z-image Increase realism & detail & sharpness

PornMaster Simple 4X Magnification Workflow

--

下載Lora Manager.

Download Lora Manager.

--

先安裝缺失的節點,並確保將插件與COMFYUI更新到最新版本。

First, install the missing nodes and ensure that the plugins and COMFYUI are updated to the latest version.

--

V2: 2026/05/22

使用此工作流時,顯示卡的記憶體最低需求為12GB。

V2版本為ZIT加ZIB的組合,採用ZIT良好解剖學的優點,並結合ZIB高清皮膚紋理的優點,可使用基於ZIB訓練的人物LORA,8步驟即可完成生成圖片。

需先下載V1版本工作流中” FaceDetailer”的相關工具。

 

下載以下三個Turbo lora:

zedTurboLightning.RIhY

Z-Image-Fun-Lora-Distill-4-Steps-2603-ComfyUI

Z-Image-Fun-Lora-Distill-8-Steps-2603-ComfyUI

 

下載以下兩個檢查站,可使用fp8或bf16版本:

PornMaster z-image Turbo V3.5_fp8

PornMaster_z-image_base_V1_fp8

 

When using this workflow, the minimum GPU memory requirement is 12GB.

Version 2 is a combination of ZIT and ZIB. It adopts the excellent anatomy quality of ZIT while incorporating the high-definition skin texture advantages of ZIB. Character LoRAs trained based on ZIB can also be used, and images can be generated in as few as 8 steps.

You must first download the tools related to “FaceDetailer” from the V1 workflow.

 

Download the following three Turbo LoRAs:

zedTurboLightning.RIhY

Z-Image-Fun-Lora-Distill-4-Steps-2603-ComfyUI

Z-Image-Fun-Lora-Distill-8-Steps-2603-ComfyUI

 

Download the following two checkpoints. You may use either the fp8 or bf16 versions:

PornMaster z-image Turbo V3.5_fp8

PornMaster_z-image_base_V1_fp8


V1:

下載 z_image_turbo_fp8_e4m3fn,或使用原版BF16的Z Image Turbo.

--

下載face_yolov9c.pt

https://huggingface.co/Bingsu/adetailer/blob/main/face_yolov9c.pt

將face_yolov9c.pt放入以下路徑:ComfyUI\models\ultralytics\bbox

--

下載sam_vit_b_01ec64.pth

將sam_vit_b_01ec64.pth放入以下路徑:ComfyUI\models\sams

--

如果面部修復功能沒有生效時,需提高"guide size"的數字.

"FaceDetailer"安裝有錯誤時,請參考"ComfyUI-Impact-Pack"中的教學.

--

四倍放大圖片需下載4x-Ultrasharp ,並將它放入以下路徑: ComfyUI\models\upscale_models.

--

Download z_image_turbo_fp8_e4m3fn, or use the original BF16 version of Z Image Turbo.

--

Download face_yolov9c.pt

https://huggingface.co/Bingsu/adetailer/blob/main/face_yolov9c.pt

Place face_yolov9c.pt in the following path:ComfyUI\models\ultralytics\bbox

--

If the facial repair function is ineffective, the "guide size" number needs to be increased.

--

If you encounter an error during the installation of "FaceDetailer", please refer to the tutorial in "ComfyUI-Impact-Pack".

--

To enlarge an image by 4x, download 4x-Ultrasharp and place it in the following path: ComfyUI\models\upscale_models.

--

Clip: qwen_3_4b.safetensors or qwen_3_8b.safetensors

Vae: ae.safetensors

--

我的其他檢查站和Lora。

My other checkpoints and Lora.

--

客製化lora:我的Telegram ID:@iamddtla0620

我的微信ID:iamddtla

我的line ID:iamddtla

時間寶貴,請直接說明來意,例如:訂製lora.

Customized lora: My Telegram ID: @iamddtla0620

My WeChat ID: iamddtla

My Line ID: iamddtla

Time is precious, please state your intention directly, for example: customized LORA.

このモデルで生成された画像