---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Polaroid
- Warm
- art
- i2i
base_model: black-forest-labs/FLUX.1-Kontext-dev
widget:
- src: images/1.jpg
  text: >-
    [photo content], in the style of a vintage Polaroid, with warm, faded tones,
    and a white border.
  prompt: >
    [photo content], in the style of a vintage Polaroid, with warm, faded tones,
    and a white border.
  output:
    url: images/2.png
instance_prompt: >-
  [photo content], in the style of a vintage Polaroid, with warm, faded tones,
  and a white border.
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/OwlnWuOr0qc_owljkqeM1.png)

# **Polaroid-Warm-i2i [Image-to-Image]**

<Gallery />

Polaroid-Warm-i2i is an adapter built for black-forest-lab's FLUX.1-Kontext-dev, designed to generate seamless vintage Polaroid-style images with warm, faded tones. The model was trained on 30 image pairs (15 start images, 15 end images) to achieve high-quality style transfer and image manipulation. Synthetic result nodes were generated using NanoBanana from Google and labeled with DeepCaption-VLA-7B. The adapter is triggered with the following prompt:

> [!note]
[photo content], in the style of a vintage Polaroid, with warm, faded tones, and a white border.


---

## Sample Inference

| ex1 | ex2 |
|------|-------|
| ![Left Screenshot](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/lFOJyUVVQ1xfPFlpVeK54.png) | ![Right Screenshot](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/C99N95TbLVjwR5nynyCD2.png) |

---

## Parameter Settings

| Setting                  | Value                    |
| ------------------------ | ------------------------ |
| Module Type              | Adapter                     |
| Base Model               | FLUX.1 Kontext Dev - fp8 |
| Trigger Words            | [photo content], in the style of a vintage Polaroid, with warm, faded tones, and a white border.   |
| Image Processing Repeats | 50                       |
| Epochs                   | 30                       |
| Save Every N Epochs      | 1                        |

    Labeling: DeepCaption-VLA-7B(natural language & English)
    
    Total Images Used for Training : 30 Image Pairs (15 Start, 15 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   | 4300  |
| Sampler | euler |

---

## Trigger words


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

You should use `in the style of a vintage Polaroid` to trigger the image generation.

You should use `with warm` to trigger the image generation.

You should use `faded tones` to trigger the image generation.

You should use `and a white border.` to trigger the image generation.


## Download model


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