Ovis 이미지용 ComfyUI 워크플로우

피드백은 항상 환영합니다.

‼️ ComfyUI를 최신 Github 버전으로 업데이트하세요‼️ 2025년 12월 3일

📂 필요한 모델

1. 분산 모델: ovis_image_bf16.safetensors .../ComfyUI/models/diffusion_models/

   • https://huggingface.co/Comfy-Org/Ovis-Image/blob/main/split_files/diffusion_models/ovis_image_bf16.safetensors

2. 텍스트 인코더: ovis_2.5.safetensors .../ComfyUI/models/text_encoders/

   • https://huggingface.co/Comfy-Org/Ovis-Image/blob/main/split_files/text_encoders/ovis_2.5.safetensors

3. VAE: ae.safetensors .../ComfyUI/models/vae/

   • https://huggingface.co/Comfy-Org/z_image_turbo/tree/main/split_files/vae

📂 선택적 모델

• 고해상도 확장 모델: 4x_foolhardy_Remacri.pth .../ComfyUI/models/upscale_models

  • https://huggingface.co/FacehugmanIII/4x_foolhardy_Remacri

• 검출 모델: face_yolov9c.pt .../ComfyUI/models/ultralytics/bbox

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

• SAM 모델: sam_vit_b_01ec64.pth .../ComfyUI/models/sams

  • https://github.com/facebookresearch/segment-anything#model-checkpoints

🧩 필요한 커스텀 노드

• 🟩 ComfyUI-Manager (Comfy-Org 제작)
  https://github.com/Comfy-Org/ComfyUI-Manager

• 🟩 rgthree-comfy (rgthree 제작)
  https://github.com/rgthree/rgthree-comfy

• 🟩 ComfyUI-Easy-Use (yolain 제작)
  https://github.com/yolain/ComfyUI-Easy-Use

• 🟩 ComfyUI-Image-Saver (alexopus 제작)
  https://github.com/alexopus/ComfyUI-Image-Saver

• 🟩 ComfyUI-Impact-Pack (ltdrdata 제작)
  https://github.com/ltdrdata/ComfyUI-Impact-Pack

• 🟩 ComfyUI-Impact-Subpack (ltdrdata 제작)
  https://github.com/ltdrdata/ComfyUI-Impact-Subpack

⚙️ 권장 설정

• 스텝: 20~50 (기본값 25)

• CFG: ~5.0 (기본값 5.0)

• 샘플러: euler

• 스케줄러: sgm_uniform 또는 simple

[1:1] 1024x1024
[3:4] 896x1152
[5:8] 832x1216
[9:16] 768x1344
[9:21] 640x1536

실험해보고 즐기세요!