注意:使用了二次採樣，或是潛空間放大，很可能會在圖片中額外的添加精液.Note: Using a second sampling pass or latent-space upscaling may cause additional semen to be added to the image.<h2 id="download-pornmaster-krea2"><a target="_blank" rel="ugc" href="https://civarchive.com/models/2735032/pornmaster-krea2?modelVersionId=3075206">Download PornMaster [Krea2]</a></h2><h2 id="pornmaster-krea2-i2i-workflow"><a target="_blank" rel="ugc" href="https://civarchive.com/models/2787374/pornmaster-krea2-i2i-workflow">PornMaster Krea2 i2i Workflow</a></h2>2026/10/10新增適合新手使用的turbo簡單工作流，沒有負面提示詞，沒有複雜插件，工作流極其精簡。Added a simple Turbo workflow suitable for beginners. No negative prompts, no complex plugins, and an extremely streamlined workflow. Lora管理器和使用教學LoRA Manager and Usage Tutorial:<a target="_blank" rel="ugc" href="https://github.com/willmiao/ComfyUI-Lora-Manager">https://github.com/willmiao/ComfyUI-Lora-Manager</a><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/hvKw31YpE-U?rel=1" start="0"></iframe></div>2026/09/17: upscale增加 "放大 latent 空間"的工作流，可用於RAW與Turbo版本。Add a workflow for upscaling in latent space, which can be used with both the RAW and Turbo versions.2026/07/25:V2工作流增加了負面提示詞，可用於RAW與Turbo版本。The V2 workflow adds negative warning words, which can be used in both RAW and Turbo versions.--這是一個簡單的工作流，我的krea2範例圖片都是用此工作流生成，內容包含基礎的文生圖(t2i)和面部修復(FaceDetailer)工作流，以及獨立的透過lora換臉工作流。工作流中不包含提示詞反推和提示詞增強工具。此工作流顯示卡記憶體最需要求為12GB。This is a simple workflow that I used to generate all of my Krea2 sample images. It includes a basic text-to-image (T2I) workflow, a FaceDetailer workflow, and a separate LoRA-based face swap workflow.This workflow does not include prompt reverse-engineering or prompt enhancement tools.The minimum GPU VRAM requirement for this workflow is 12 GB.下載<a target="_blank" rel="ugc" href="https://github.com/willmiao/ComfyUI-Lora-Manager">Lora Manager.</a>Download <a target="_blank" rel="ugc" href="https://github.com/willmiao/ComfyUI-Lora-Manager">Lora Manager</a>.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_<a target="_blank" rel="ugc" href="http://yolov9c.pt">yolov9c.pt</a><a target="_blank" rel="ugc" href="https://huggingface.co/Bingsu/adetailer/blob/main/face_yolov9c.pt">https://huggingface.co/Bingsu/adetailer/blob/main/face_yolov9c.pt</a>將face_<a target="_blank" rel="ugc" href="http://yolov9c.pt">yolov9c.pt</a>放入以下路徑:ComfyUI\models\ultralytics\bbox--下載<a target="_blank" rel="ugc" href="https://huggingface.co/datasets/Gourieff/ReActor/blob/main/models/sams/sam_vit_b_01ec64.pth">sam_vit_b_01ec64.pth</a>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"<a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Impact-Pack">ComfyUI-Impact-Pack</a>"中的教學.--Download face_<a target="_blank" rel="ugc" href="http://yolov9c.pt">yolov9c.pt</a><a target="_blank" rel="ugc" href="https://huggingface.co/Bingsu/adetailer/blob/main/face_yolov9c.pt">https://huggingface.co/Bingsu/adetailer/blob/main/face_yolov9c.pt</a>Place face_<a target="_blank" rel="ugc" href="http://yolov9c.pt">yolov9c.pt</a> 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 "<a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Impact-Pack">ComfyUI-Impact-Pack</a>".--text_encoders<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Krea-2/resolve/main/text_encoders/qwen3vl_4b_fp8_scaled.safetensors">qwen3vl_4b_fp8_scaled.safetensors</a></li></ul><a target="_blank" rel="ugc" href="https://huggingface.co/Winnougan/Comfy-Qwen3-VL-INT8/blob/main/qwen3vl_4b_int8_convrot.safetensors">qwen3vl_4b_int8_convrot.safetensors</a>vae<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Krea-2/resolve/main/vae/qwen_image_vae.safetensors">qwen_image_vae.safetensors</a></li><li></li></ul>我已將模型上傳至<a target="_blank" rel="ugc" href="https://www.runninghub.ai/user-center/1968577612886994945?inviteCode=rh-v1304">runninghub</a>。I have uploaded the model to <a target="_blank" rel="ugc" href="https://www.runninghub.ai/user-center/1968577612886994945?inviteCode=rh-v1304">runninghub</a>.--<a target="_blank" rel="ugc" href="https://civarchive.com/user/iamddtla/collections">我的其他檢查站和Lora。</a><a target="_blank" rel="ugc" href="https://civarchive.com/user/iamddtla/collections">My other checkpoints and Lora.</a>--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: @iamddtla0620My WeChat ID: iamddtlaMy Line ID: iamddtlaTime is precious, please state your intention directly, for example: customized LORA.

PornMaster Krea2 Turbo T2I Workflow

2026/09/17: upscale增加 "放大 latent 空間"的工作流，可用於RAW與Turbo版本。Add a workflow for upscaling in latent space, which can be used with both the RAW and Turbo versions.

Files with SHA256: ae98a2362f3aba094d557344e6a603c18c2bd4b4163e64aea220dc43f442e574