---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- sketch
- pencil
- monochrome
- art
widget:
- src: images/1.jpg
  text: >-
    [photo content], replicate the image as a pencil illustration, black and
    white, with sketch-like detailing.
  prompt: >
    [photo content], replicate the image as a pencil illustration, black and
    white, with sketch-like detailing.
  output:
    url: images/2.png
base_model: black-forest-labs/FLUX.1-Kontext-dev
instance_prompt: >-
  [photo content], replicate the image as a pencil illustration, black and
  white, with sketch-like detailing.
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/SSbZ2xihTKCkspLTn69kw.png)

# **Monochrome-Pencil-i2i [Image-to-Image]**

<Gallery />

Monochrome-Pencil-i2i is an adapter for black-forest-lab's FLUX.1-Kontext-dev. It is a Sketch LoRA trained for seamless conversion of any image into a monochrome pencil sketch while preserving the original characteristics of the image. The model was trained on 40 image pairs (20 start images, 20 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], replicate the image as a pencil illustration, black and white, with sketch-like detailing.

---

## Sample Inference

| FLUX.1-Kontext-dev |<span style="color:red">Monochrome-Pencil</span> |
|------|-------|
| ![Left Screenshot](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/vJ29Ijc0bRDheKPisKwHi.png) | ![Right Screenshot](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/Q0DRFoTGa0czAf8sV4Jgn.png) |


| ex1-<span style="color:red">Monochrome-Pencil</span> | ex2-<span style="color:red">Monochrome-Pencil</span> |
|------|-------|
| ![Left Screenshot](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/qQKVgRDwhi2asBt5VdUo3.png) | ![Right Screenshot](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/y51D0wxOZCx95J4jGP_k6.png) |

---

## Parameter Settings

| Setting                  | Value                    |
| ------------------------ | ------------------------ |
| Module Type              | Adapter                     |
| Base Model               | FLUX.1 Kontext Dev - fp8 |
| Trigger Words            | [photo content], replicate the image as a pencil illustration, black and white, with sketch-like detailing. |
| Image Processing Repeats | 50                       |
| Epochs                   | 25                       |
| Save Every N Epochs      | 1                        |

    Labeling: DeepCaption-VLA-7B(natural language & English)
    
    Total Images Used for Training : 40 Image Pairs (20 Start, 20 End)

    Synthetic result nodes were generated using NanoBanana from Google and SeedDream 4 (dataset for result sets)
    

## 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   | 3900  |
| Sampler | euler |

---

## Trigger words

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

You should use `replicate the image as a pencil illustration` to trigger the image generation.

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

You should use `with sketch-like detailing.` to trigger the image generation.


## Download model

 
[Download](/prithivMLmods/Monochrome-Pencil/tree/main) them in the Files & versions tab.