---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- photo
- restore
- art
widget:
- src: images/1.jpg
  text: >-
    [photo content], restore and enhance the image by repairing any damage, scratches, or fading. Colorize the photo naturally while preserving authentic textures and details, maintaining a realistic and historically accurate look.
  prompt: >
    [photo content], restore and enhance the image by repairing any damage, scratches, or fading. Colorize the photo naturally while preserving authentic textures and details, maintaining a realistic and historically accurate look..
  output:
    url: images/2.webp
base_model: black-forest-labs/FLUX.1-Kontext-dev
instance_prompt: >-
  [photo content], restore and enhance the image by repairing any damage,
  scratches, or fading. Colorize the photo naturally while preserving authentic
  textures and details, maintaining a realistic and historically accurate look.
license: other
license_name: flux-1-dev-non-commercial-license
license_link: LICENSE.md
pipeline_tag: image-to-image
---

![1.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/n4pmb4XGZh4y1Nxi0z9cn.png)

# **Photo-Restore-i2i [Image-to-Image]**

<Gallery />

Photo-Restore-i2i is an adapter for black-forest-lab's FLUX.1-Kontext-dev, designed to restore old photos into mid-colorized, detailed images. The model was trained on 50 image pairs (25 start images, 25 end images). Synthetic result nodes were generated using NanoBanana from Google and SeedDream 4 (dataset for result sets), and labeled with DeepCaption-VLA-7B. The adapter is triggered with the following prompt:

> [!note]
[photo content], restore and enhance the image by repairing any damage, scratches, or fading. Colorize the photo naturally while preserving authentic textures and details, maintaining a realistic and historically accurate look.

---

## Sample Inference

| ex1 | ex2 |
|------|-------|
| ![Left Screenshot](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/g--KoNLNm45CzOByLkokN.png) | ![Right Screenshot](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/zBL4ZAapuRgrfQCu0-zga.png) |

---

## Parameter Settings

| Setting                  | Value                    |
| ------------------------ | ------------------------ |
| Module Type              | Adapter                     |
| Base Model               | FLUX.1 Kontext Dev - fp8 |
| Trigger Words            | [photo content], restore and enhance the image by repairing any damage, scratches, or fading. Colorize the photo naturally while preserving authentic textures and details, maintaining a realistic and historically accurate look. |
| Image Processing Repeats | 50                       |
| Epochs                   | 28                       |
| Save Every N Epochs      | 1                        |

    Labeling: DeepCaption-VLA-7B(natural language & English)
    
    Total Images Used for Training : 50 Image Pairs (25 Start, 25 End)

    Synthetic Result Node generated by NanoBanana from Google (Image Result Sets Dataset)
    

## Training Parameters

| Setting                     | Value     |
| --------------------------- | --------- |
| Seed                        | -         |
| Clip Skip                   | -         |
| Text Encoder LR             | 0.00001   |
| UNet LR                     | 0.00005   |
| LR Scheduler                | constant  |
| Optimizer                   | AdamW8bit |
| Network Dimension           | 64        |
| Network Alpha               | 32        |
| Gradient Accumulation Steps | -         |

## Label Parameters

| Setting         | Value |
| --------------- | ----- |
| Shuffle Caption | -     |
| Keep N Tokens   | -     |

## Advanced Parameters

| Setting                   | Value |
| ------------------------- | ----- |
| Noise Offset              | 0.03  |
| Multires Noise Discount   | 0.1   |
| Multires Noise Iterations | 10    |
| Conv Dimension            | -     |
| Conv Alpha                | -     |
| Batch Size                | -     |
| Steps   | 4100  |
| Sampler | euler |

---

## Trigger words

You should use `[photo content]` to trigger the image generation.

You should use `restore and enhance the image by repairing any damage` to trigger the image generation.

You should use `scratches` to trigger the image generation.

You should use `or fading. Colorize the photo naturally while preserving authentic textures and details` to trigger the image generation.

You should use `maintaining a realistic and historically accurate look.` to trigger the image generation.


## Download model


[Download](/prithivMLmods/Photo-Restore-i2i/tree/main) them in the Files & versions tab.