SDXL Inpainting
Video Lecture
| Section | Video Links |
|---|---|
| SDXL Inpainting |  |
Description
We can use the inpainting technique using SDXL.
We can use a specific SDXL inpainting base and merge it with any of our other SDXL based checkpoints to maximise consistency.
Download diffusion_pytorch_model.fp16.safetensors from https://huggingface.co/diffusers/stable-diffusion-xl-1.0-inpainting-0.1/tree/main/unet (5.14 GB) and rename to sd_xl_inpainting_fp16.safetensors.
Copy it into your ComfyUI/models/checkpoints/ folder.
📂 ComfyUI/
├── 📂 models/
│ ├── 📂 checkpoints/
│ │ └── sd_xl_inpainting_fp16.safetensors
| Initial Image | Workflow |
|---|---|
 |
 |
This example workflow uses,
- Realism Engine SDXL checkpoint.
- ComfyUI Image Compare Tool
In the video, we will change the hair color, add glasses and change the clothes.
WGET Commands
If you are using Runpod, or a similar hosted GPU service, then you can access your running pod/instance using a terminal.
# # | |
Wait for files to download fully before running your workflows.