CoolFace
Modelpublic

sunseeker001/Monochrome-Pencil

sourceHugging Faceotherupdated 6mo agoView on Hugging Face
0likes25downloads
Model Card

1.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 ScreenshotRight Screenshot
ex1-<span style="color:red">Monochrome-Pencil</span>ex2-<span style="color:red">Monochrome-Pencil</span>
Left ScreenshotRight Screenshot

Parameter Settings

SettingValue
Module TypeAdapter
Base ModelFLUX.1 Kontext Dev - fp8
Trigger Words[photo content], replicate the image as a pencil illustration, black and white, with sketch-like detailing.
Image Processing Repeats50
Epochs25
Save Every N Epochs1

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

SettingValue
Seed-
Clip Skip-
Text Encoder LR0.00001
UNet LR0.00005
LR Schedulerconstant
OptimizerAdamW8bit
Network Dimension64
Network Alpha32
Gradient Accumulation Steps-

Label Parameters

SettingValue
Shuffle Caption-
Keep N Tokens-

Advanced Parameters

SettingValue
Noise Offset0.03
Multires Noise Discount0.1
Multires Noise Iterations10
Conv Dimension-
Conv Alpha-
Batch Size-
Steps3900
Samplereuler

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 them in the Files & versions tab.