ComfyUI - Lossless Edit — FLUX Kontext Dev
Remove/edit any object with lossless quality - Flux Kontext Dev & Flow Assistor (ComfyUI)
Runtime profile
- Access
- External workflow
- Status
- Listed
- Source
- Civitai
- Updated
- Sep 22, 2026
Source description
Remove/edit any object with lossless quality - Flux Kontext Dev & Flow Assistor (ComfyUI)
Instead of editing the whole image at once, which reduces output quality and size and loses details, use a unique workflow to edit a specially selected area of the image; do not touch other parts of the image. Change colors, remove watermarks and logos, fix artifacts, remove text, fill broken parts, etc.
Early access on Patreon (support): https://www.patreon.com/mm744
What you need
- Model files
- 9.9 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Requirements
Models
4- File unverified
VAE · Hugging Face · Comfy-Org/Lumina_Image_2.0_Repackaged · Lumina Image 2.0 Repackaged
- File unverified
Text encoder · Hugging Face · comfyanonymous/flux_text_encoders · Flux Text Encoders
flux1-dev-kontext_fp8_scaled.safetensors
File unverifiedCheckpoint · Hugging Face · Comfy-Org/flux1-kontext-dev_ComfyUI
t5xxl_fp8_e4m3fn_scaled.safetensors
File unverifiedText encoder · Hugging Face · comfyanonymous/flux_text_encoders · Flux Text Encoders
Node packs
1comfyui-flow-assistor
FoundNode pack · Registry
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Purpose
ComfyUI - Lossless Edit is for targeted image editing: it takes an image and a specially selected area, changes that area, and produces an edited image while leaving other parts untouched.
Flow
It can change colors, remove watermarks and logos, fix artifacts, remove text, and fill broken parts.
Inputs and outputs
Input: an image and a specially selected area to edit. Output: an edited image with that area changed.
Setup
This is a ComfyUI workflow from MM744 based on Flux.1 Kontext.
Dependencies
The listed model files are ae.safetensors, clip_l.safetensors, flux1-dev-kontext_fp8_scaled.safetensors, and t5xxl_fp8_e4m3fn_scaled.safetensors.
It also uses the comfyui-flow-assistor node pack at version 1.0.2.
Configuration
Select the area you want to change so the edit stays directed at that part of the image.
Suggestion · not verified
Cautions
Before using it, verify that the four model files and comfyui-flow-assistor are available in your ComfyUI setup.
Suggestion · not verified
No license is listed for this workflow.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 source
Sources
1 sourceSource excerpts
1 excerpt
Source excerpts
1 excerptSource context: 165 downloads · Type Workflows · Base model Flux.1 Kontext
