所有範例圖片皆由AI生成。

All example images are generated by AI.

此工作流建議顯示卡記憶體最低為12GB.

This workflow recommends a minimum of 12GB of graphics card memory.

Download PornMaster [Flux.2 Klein 9B]

下載Lora Manager.

Download Lora Manager.

可以將Lora Manager替換成"Power Lora Loader (rgthree)".

You can replace Lora Manager with "Power Lora Loader (rgthree)". 

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. (或是重新啟動COMFYUI)

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

--

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

--

If the facial repair function is ineffective, the "guide size" number needs to be increased. (Or restart COMFYUI)

--

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

--

使用英文提示詞的精準度會更高。

Using English prompts will result in higher accuracy.

--

注意如果原始照片解析度太低或過於模糊，生成的圖片可能產生鋸齒狀.

Note that if the original photo has too low a resolution or is too blurry, the generated image may have jagged edges.

--

text_encoders

· qwen_3_8b_fp8mixed.safetensors

vae

· flux2-vae.safetensors

· or full_encoder_small_decoder.safetensors

--

我已將模型上傳至runninghub。

I have uploaded the model to runninghub.

--

我的其他檢查站和Lora。

My other checkpoints and Lora.

--

不要問我如何安裝的問題與comfyui如何使用。

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.

Do not ask me questions about how to install it or how to use ComfyUI.

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.