ComfyUI Workflow for Ovis Image

Any feedback would be appreciated.

‼️Update your ComfyUI to the latest Github version‼️3rd Dec. 2025

📂 Required Models

1. Diffusion Model: ovis_image_bf16.safetensors .../ComfyUI/models/diffusion_models/

   • Encoder: ovis_2.5.safetensors .../ComfyUI/models/text_encoders/

     • ae.safetensors .../ComfyUI/models/vae/

       • id="optional-models">📂 Optional Models

         • Upscale Model: 4x_foolhardy_Remacri.pth .../ComfyUI/models/upscale_models

           • Model: face_yolov9c.pt .../ComfyUI/models/ultralytics/bbox

             • Model: sam_vit_b_01ec64.pth .../ComfyUI/models/sams

               • />

                 🧩 Required Custom Nodes

                 • 🟩 ComfyUI-Manager (by Comfy-Org)
                   rgthree-comfy (by rgthree)
                   style="color:rgb(34, 139, 230)"> ComfyUI-Easy-Use (by yolain)
                   ComfyUI-Image-Saver (by alexopus)
                   ComfyUI-Impact-Pack (by ltdrdata)
                   style="color:rgb(34, 139, 230)"> ComfyUI-Impact-Subpack (by ltdrdata)
                   />

                   ⚙️ Recommended Settings

                   • Steps: 20 to 50 (Default set to 25).

                   • CFG: ~5.0 (Default set to 5.0).

                   • Sampler: euler

                   • Scheduler: sgm_uniform or simple

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

                   Experiment and enjoy!

                   ---