CFG:1，4 steps.
CFG:1.5，5~8 steps.
--
下載Lora Manager.
下載Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI lora.
將Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI lora的lora權重設定為1。
--
Download Lora Manager.
Download Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI lora.
Set the lora weight of Z-Image-Fun-Lora-Distill-4-Steps-2602-ComfyUI lora to 1.
--
先安裝缺失的節點.
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
--
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
“放大 latent 空間”中的”去雜訊強度”數字越大整題構圖的改變將會越大。
--
Install the missing nodes first.
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
--
Download sam_vit_b_01ec64.pth
Place sam_vit_b_01ec64.pth in the following path: ComfyUI\models\sams
--
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.
The larger the "denoise" number in "Enlarge the latent space", the greater the change in the overall structure of the problem.
text_encoders
diffusion_models
vae