[Workflow] AingMixKrea + FaceDetailer[1] What this workflow does Stage 1 (Base generation) : Generates the image with AingMixKrea Stage 2 (Face refinement) : FaceDetailer detects the face and redraws it[2] Requirements- Latest version of ComfyUI- Tested and working on 8GB VRAM (RTX 4060 Ti); more VRAM is better. - 32GB+ system RAM recommended.[3] Required custom nodes ComfyUI Impact Pack ComfyUI Impact Subpack rgthree-comfy ControlAltAI Nodes Comfyui_LG_Tools gguf (calcuis)[4] Required model files and where to put them ◆ Stage 1: Base generation (Krea2) ComfyUI\models\diffusion_models\KREA2\AingMixKrea-int8_convrot.safetensors (~13.5GB) - <a target="_blank" rel="ugc" href="https://civarchive.com/models/3012914/aingmix-krea2-kroma-pussy-loras">https://civarchive.com/models/3012914/aingmix-krea2-kroma-pussy-loras</a> ComfyUI\models\text_encoders\Huihui-Qwen3-VL-4B-Instruct-abliterated.safetensors (~8.9GB) - <a target="_blank" rel="ugc" href="https://huggingface.co/ahmed22xa/Huihui-Qwen3-VL-4B-Instruct-abliterated-comfy">https://huggingface.co/ahmed22xa/Huihui-Qwen3-VL-4B-Instruct-abliterated-comfy</a> ComfyUI\models\vae\qwen_image_vae.safetensors (~254MB) - <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae">https://huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/tree/main/split_files/vae</a> ◆ Stage 2: Face detailer (Z-Image Turbo) ComfyUI\models\diffusion_models\moodyRealMix_zitV7.safetensors (~12.3GB) - <a target="_blank" rel="ugc" href="https://civarchive.com/models/621441/moody-real-mix?modelVersionId=3005060">https://civarchive.com/models/621441/moody-real-mix?modelVersionId=3005060</a> ComfyUI\models\text_encoders\qwen_3_4b.safetensors (~8GB) - <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/text_encoders">https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/text_encoders</a> ComfyUI\models\vae\ae-zit.safetensors (~335MB) - <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/vae">https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/vae</a> ComfyUI\models\loras\ai-friend.safetensors - <a target="_blank" rel="ugc" href="https://civarchive.com/models/2996379/a-ing-korean-cute-girl">https://civarchive.com/models/2996379/a-ing-korean-cute-girl</a> ◆ Face detection (Impact Pack) ComfyUI\models\ultralytics\bbox\face_<a target="_blank" rel="ugc" href="http://yolov8m.pt">yolov8m.pt</a> - <a target="_blank" rel="ugc" href="https://huggingface.co/Bingsu/adetailer/tree/main">https://huggingface.co/Bingsu/adetailer/tree/main</a> ComfyUI\models\sams\sam_vit_b_01ec64.pth - <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/Gourieff/ReActor/blob/main/models/sams/sam_vit_b_01ec64.pth">https://huggingface.co/datasets/Gourieff/ReActor/blob/main/models/sams/sam_vit_b_01ec64.pth</a>[5] How to use1. Drag json onto the ComfyUI canvas to load it2. install the custom nodes in [3] and restart3. Check that each loader node has the correct model selected4. Type prompt5. Pick the aspect ratio / megapixels in the "resolution" node6. Have fun

Files with SHA256: 341fbd8fbee3fab84ae5ee4b8d58badacdb93e1951eb77374602770557088d2a