ComfyUI model file · Checkpoint (SDXL inpainting)

juggernautXL_versionXInpaint.safetensors

Juggernaut XL X Inpainting · SDXL inpainting checkpoint based on Juggernaut X

juggernautXL_versionXInpaint.safetensors is the Civitai download name for juggernautXL_juggernautX_inpainting.safetensors, an SDXL inpainting checkpoint built from Juggernaut X. Put it in ComfyUI/models/checkpoints, load it with Load Checkpoint, and feed it a masked image through VAE Encode (for Inpainting).

  • SDXL
  • Inpainting
  • 6.94 GB
  • Juggernaut X
Download · 6.94 GB

This is a community inpainting conversion (by WereCatf), not an official RunDiffusion release. The base Juggernaut X model is a separate file.

juggernautXL_versionXInpaint.safetensors

Same file as
juggernautXL_juggernautX_inpainting.safetensors
Type
Checkpoint (SDXL inpainting)
Format
Safetensors · fp16
Size
6.94 GB (6,938,072,258 bytes)
SHA256
b1689257…bfe1fbc00
ComfyUI folder
models/checkpoints/
Loader node
Load Checkpoint
Released
Apr 20, 2024 · Civitai upload
SHA256 and size from Civitai API (model 403361, version 456538), checked by RunComfy on .

The short version

What is juggernautXL_versionXInpaint.safetensors?

Juggernaut X is a popular photorealistic SDXL model from RunDiffusion. Regular checkpoints inpaint poorly because they never see the masked image. This conversion adds SDXL’s inpainting input channels so the model blends new content into the unmasked area.

The Civitai listing “Juggernaut XL inpainting” stores it as juggernautXL_juggernautX_inpainting.safetensors. Downloading the “Version X Inpaint” version names it juggernautXL_versionXInpaint.safetensors, which is the name shared workflows tend to use.

Install

Download and install juggernautXL_versionXInpaint.safetensors

Where it goes
ComfyUI/
└─ models/
   ├─ …
   └─ checkpoints/
      └─ juggernautXL_versionXInpaint.safetensors
terminal · Linux / macOS
$ cd ComfyUI/models/checkpoints# Download it from Civitai · Juggernaut XL inpainting, then save it here as:# juggernautXL_versionXInpaint.safetensors$ sha256sum juggernautXL_versionXInpaint.safetensors# b1689257e6e1b2e61544b1a41fc114e7d798f68854b3f875cd52070bfe1fbc00

Safetensors files hold tensors only and cannot run code. Still compare the SHA256: a failed download often leaves an HTML error page saved under the model’s filename.

Use

How to load juggernautXL_versionXInpaint.safetensors in ComfyUI

Inpainting checkpoints expect the masked image as extra input channels. Load Checkpoint reads the file, and VAE Encode (for Inpainting) builds the masked latent from your image and mask.

Minimal graph. Click a node to open its reference page.
  • Keep denoise at 1.0

    VAE Encode (for Inpainting) blanks the masked area, so lower denoise leaves grey patches.

  • Soft edits instead

    For subtle changes, use InpaintModelConditioning with a lower denoise.

Compare

Same file, other names, and alternatives

FileRelationSizeBest for
juggernautXL_versionXInpaint.safetensorsThis page · Civitai download name6.94 GBInpainting with Juggernaut X
juggernautXL_v9Rundiffusionphoto2.inpainting.safetensorsSame listing · Juggernaut v9 inpaint6.94 GBOlder v9 look
juggernautXL_XI.inpainting.safetensorsOther uploader · Juggernaut XI inpaint6.94 GBNewer Juggernaut XI base
Juggernaut_X_RunDiffusion.safetensorsBase model · not for inpainting7.11 GBText to image

Troubleshoot

Common errors and fixes

Value not in list: ckpt_name: 'juggernautXL_versionXInpaint.safetensors' not in [...]

Why: The workflow asks for this exact filename, but ComfyUI cannot find it in models/checkpoints. Usually the file is missing, sits in a different folder, or was saved under another name such as juggernautXL_juggernautX_inpainting.safetensors.

Fix: Move the file into ComfyUI/models/checkpoints/, rename it to match the workflow (or pick it again in the dropdown), then refresh the node list or restart ComfyUI.

RuntimeError: Given groups=1, weight of size [320, 9, 3, 3], expected input to have 9 channels, but got 4

Why: Inpainting checkpoints expect 9 input channels (latent, mask and masked image). A plain VAE Encode only gives 4.

Fix: Use VAE Encode (for Inpainting) or InpaintModelConditioning instead of VAE Encode.

SafetensorError: Error while deserializing header

Why: The download is incomplete, or the browser saved an HTML sign-in or error page under the model’s filename.

Fix: Check that the file is exactly 6,938,072,258 bytes and that its SHA256 matches the value above. Download it again from Civitai · Juggernaut XL inpainting if not.

FAQ

juggernautXL_versionXInpaint.safetensors FAQ

Can I use it for text to image?

It works, but the regular Juggernaut X checkpoint gives better text-to-image results. Use this one only for inpainting and outpainting.

Where do I put juggernautXL_versionXInpaint.safetensors in ComfyUI?

In ComfyUI/models/checkpoints/. Then refresh the node list or restart ComfyUI so Load Checkpoint lists the file.

Which ComfyUI node loads juggernautXL_versionXInpaint.safetensors?

Load Checkpoint. It is built into ComfyUI, so no custom nodes are needed.

Can I use juggernautXL_versionXInpaint.safetensors commercially?

Civitai’s listing allows commercial use of generated images and renting the model on generation services, but not selling the model or merges of it.

Sources: Civitai model 403361 · Juggernaut XL on Civitai

RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.