AI-powered photo restoration using Kevin Image Edit

The Kevin Image Edit and Image Edit 2509 are two extremely versatile models that bring photo editing power like never before. As shown in some of the past videos its super easy to setup locally and use with simple prompts. If you want to learn how to point, I recommend you take a look at it Post.

I got into restoring and recoloring old and vintage photos that haven’t stood the test of time, and the results were amazing. Within seconds to two minutes, I could see beautifully restored images produced by FluxContext.

immediate

The gesture isn’t complicated and by studying the images I started to describe what I wanted Kevin Image Addity to do and slowly build the gesture down over time. This works in most cases.

restore and colorize this photo, remove the stains, dust spots, noise, scratches and stripes from the image, fill in any gaps, ripped or torn sections, turning it into a high quality photograph, reversal film photography, remove stains and crease marks, repair gaps and fold or bends

If you want to keep the black and white look of the image, I’ll explain that at the beginning and make a reference to coloring or tinting the image.

what do you need

You need to download the models below and save them in the locations as shown below. If your comfyui is not up to date, please make sure you update it to the latest version.

Diffusion model

Vae

Text Encoder

Model storage location

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   └── qwen_image_edit_

Once the models are installed, make sure you restart Comfui when you were downloading the models.

Workflow

The workflow is based on the default workflow provided by the COMFYUI team, so if you have updated COMFYUI as recommended above, you should see in the templates. You can start using one called “Flux Context Dev (grouped)“

This grouped workflow combines a group of existing base nodes to create a custom one Flux Context Image Edit A grouped node. It can be used to easily stack and build modifications to your Comfy workflow.

I modified this workflow to create my own variations and since most people want the workflow shown in my video I have provided it above. You can download it to use with your own setup. I added a Image stitching Nodes that compare the before and after with each other and save it as a JPG.

Below you see two steps where the first step does the restoration and then the second step only colors the sweater that the woman is wearing. If you don’t need the second step you can ignore these nodes, if you do the image output of the first step Edit the image K Image stitching.

The results are great in most cases and produce some well-restored images that will shave off hours of clone/stamp or adaptive/generative fill using Photoshop.

Here are some samples that were created straight from this workflow without further modification. I hope you will try it and be able to renew some beautiful memories for your loved ones.

If you would like to support our site, please consider buying us Co-Fifor , for , for , . Grab a product or Subscribe. Need a faster GPU, get access to the fastest GPUs for less than $1 per hour runpod.io