# SD XL Multi ControlNet Inpainting in diffusers

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsd-xl-multi-controlnet-inpainting-in-diffusers%2F54516%3E%5C
**Category:** 🧨 Diffusers\
**Created:** [September 11, 2023, 6:26pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsd-xl-multi-controlnet-inpainting-in-diffusers%2F54516 "2023-09-11T18:26:35Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ajkrish95](https://avatars.discourse-cdn.com/v4/letter/a/779978/32.png) [@ajkrish95](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fajkrish95)%5C
**Post date:** [September 11, 2023, 6:26pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fsd-xl-multi-controlnet-inpainting-in-diffusers%2F54516%2F1 "2023-09-11T18:26:35Z")

</div>

Our current pipeline uses multi controlnet with canny and inpaint and use the controlnetinpaint pipeline

Is the inpaint control net checkpoint available for SD XL?

Reference Code:

```
        controlnet_inpaint_model = ControlNetModel.from_pretrained(
            CONTROLNET_INPAINT_MODEL_ID, torch_dtype=torch.float16, cache_dir=DIFFUSION_CHECKPOINTS_PATH).to(
            MODEL_DEVICE)
        controlnet_hed_model = ControlNetModel.from_pretrained(
            CONTROLNET_HED_MODEL_ID, torch_dtype=torch.float16, cache_dir=DIFFUSION_CHECKPOINTS_PATH).to(
            MODEL_DEVICE)
        controlnet_canny_model = ControlNetModel.from_pretrained(
            CONTROLNET_CANNY_MODEL_ID, torch_dtype=torch.float16, cache_dir=DIFFUSION_CHECKPOINTS_PATH).to(
            MODEL_DEVICE)
        controlnet_depth_model = ControlNetModel.from_pretrained(
            CONTROLNET_DEPTH_MODEL_ID, torch_dtype=torch.float16, cache_dir=DIFFUSION_CHECKPOINTS_PATH).to(
            MODEL_DEVICE)

        self.inpaint_pipeline = StableDiffusionControlNetInpaintPipeline.from_pretrained(
            CUSTOM_SD_MODEL,
            controlnet=[controlnet_inpaint_model, controlnet_hed_model],
            torch_dtype=torch.float16).to(MODEL_DEVICE)

```