Skip to content
WorkflowListedExternal
Open source

ComfyUI inpaint workflow | Updated for anima — 1.5 V3.05

Added ability to use segmentation

Sourcecivitai.com/models/128556
TaskImage editFamilyStable DiffusionVersionRelease 236213 — PotatCat_ComfyUi_Inpaint_V3.05.jsonEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
PotatCat_ComfyUi_Inpaint_V3.05.json
Source
Civitai
Updated
Oct 18, 2026

Source description

Added ability to batch

Added ability to use segmentation

What you need

Hardware and download-size estimates are not available yet.

Requirements

Models

3

  • control_v11f1e_sd15_tile.pth

    Not resolved

    ControlNet · Unknown

  • lazylatte_v1.safetensors

    Not resolved

    Checkpoint · Unknown

  • vae-ft-mse-840000-ema-pruned.vae.pt

    Not resolved

    VAE · Unknown

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • This ComfyUI inpainting workflow is for editing images with an input image, mask, and text prompt; it is described as supporting full-image inpainting and segmentation, with preview and saved image outputs.

Flow

  • The named components cover image loading, image-to-mask conversion, text encoding, sampling, previewing, and image saving.

Inputs and outputs

  • The edit mode is described for simple changes such as changing clothes or adding items; the LoRA limits the edit, while other parts generally stay the same.

  • PreviewImage and SaveImage are named for previewing and saving image results.

Setup

  • The listed release is version 1.5 V3.05 for SD 1.5, published by PotatCat.

  • This item is a workflow rather than a Pipe, so a Pipe version does not apply.

Dependencies

  • The named model files are control_v11f1e_sd15_tile.pth, lazylatte_v1.safetensors, and vae-ft-mse-840000-ema-pruned.vae.pt.

  • The workflow names these components: LoadImage, ImageToMask, CLIPTextEncode, ScheduleToCond, ScheduleToModel, CheckpointLoaderSimple, CLIPSetLastLayer, VAELoader, VAEEncode, SetLatentNoiseMask, and LatentDuplicator.

  • It also names GroundingDinoModelLoader (segment anything), GroundingDinoSAMSegment (segment anything), SAMModelLoader (segment anything), ScaledSoftControlNetWeights, GrowMaskWithBlur, Inpaint Segments, MaskToImage, ControlNetLoaderAdvanced, Combine and Paste, JinjaRender, Prompt

Configuration

  • You can adjust mask opacity and set colormatch to 1; this setting is intended to try to match image color when a VAE, model, or LoRA changes it.

    Suggestion · not verified

  • For edit mode, use an edit LoRA with Cosmos Reference; the node and LoRA are described as necessary, and the example uses Denoise: 1.

    Suggestion · not verified

  • If shading or a shadow from the original image appears, raise “Expand mask area.”

    Suggestion · not verified

Cautions

  • The guide is outdated, the anima release is labeled beta, and bypasser/muter does not work with subgraph.

  • An older 1.5 path is described as untested, and the named components have no confirmed connections; verify the version, model files, and ImageToMask before use.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 236213
civitai.com/models/128556

Verified Oct 18

Source excerpts

3 excerpts
NoteOct 18civitai.com/models/128556

Source context: 22672 downloads · Type Workflows · Base model SD 1.5

NoteSep 6civitai.com/models/128556

Source context: 21675 downloads · Type Workflows · Base model SD 1.5

NoteJul 28civitai.com/models/128556

Source context: 20416 downloads · Type Workflows · Base model SD 1.5