---
title: embroidery-patch-kontext-dev-lora
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/embroidery-patch-kontext-dev-lora"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/embroidery-patch-kontext-dev-lora.md"
repository: AI-ModelScope/embroidery-patch-kontext-dev-lora
last_updated: 2026-06-16
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - black-forest-labs/FLUX.1-Kontext-dev
base_model_relation: adapter
parameters: 76.6M
tensor_type:
  - F32
library_name:
  - lora
  - diffusers
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
supports_inference: txt2img
downloads: 180
stars: 1
tags:
  - flux
  - image-to-image
  - lora
  - fal
  - diffusers
  - ilkerzgi
  - embroidery
---

# embroidery-patch-kontext-dev-lora

> embroidery-patch-kontext-dev-lora - AI-ModelScope 在 ModelScope 开源的模型。Embroidery Style Kontext Dev LoRA

AI-ModelScope/embroidery-patch-kontext-dev-lora 是 ModelScope 魔搭社区上的 76.6M 参数text-to-image-synthesis模型，采用 other 许可，基于 black-forest-labs/FLUX.1-Kontext-dev 构建，并支持在线推理（txt2img）。

- **Repository**: AI-ModelScope/embroidery-patch-kontext-dev-lora
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 76.6M
- **Base model**: black-forest-labs/FLUX.1-Kontext-dev
- **Online inference**: txt2img
- **Tags**: flux, image-to-image, lora, fal, diffusers, ilkerzgi, embroidery
- **Downloads**: 180
- **Stars**: 1
- **Last updated**: 2026-06-16

Source: https://www.modelscope.cn/models/AI-ModelScope/embroidery-patch-kontext-dev-lora

---

# Embroidery Style Kontext Dev LoRA

<Gallery />

This is a LoRA (Low-Rank Adaptation) model that has been trained to transform input images into an embroidery style.

## Table of Contents
- [Model Details](#model-details)
- [Uses](#uses)
- [Training](#training)

## Model Details

**Model Description:** This model is a LoRA fine-tune of `black-forest-labs/FLUX.1-Kontext-dev`. It's designed to be used in an image-to-image pipeline to apply a specific artistic style. When prompted with "make it in embroidery style", it converts regular images into embroidery-style artwork. For a red and black colored embroidery effect, you can use "make it in embroidery style, red and black colored".

* **Trained by:** [ilkerzgi](https://huggingface.co/ilkerzgi)
* **Model Type:** LoRA for Image Edit
* **Language(s):** English
* **License:** [flux1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev/blob/main/LICENSE.md)
* **Parent Model:** [black-forest-labs/FLUX.1-Kontext-dev](https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev)
* **Resources for more information:**
  * [Download the weights](https://huggingface.co/ilkerzgi/embroidery-style-kontext-dev-lora/resolve/main/hr-puSFwzOyE6TqTjybFC_adapter_model.safetensors)
  * [Try the model directly on fal.ai](https://fal.ai/models/fal-ai/flux-kontext-lora/playground?requestId=4a340b33-fd4a-4741-9fe1-3eeafd336115)

## Uses

#### Direct Use
This model is intended to be used for artistic image generation. You can use it to apply an "embroidery style" to your own images. The model works best when using the trigger phrase: "**make it in embroidery style**". 

#### Usage Recommendations
* **Best for:** 2D drawings with solid backgrounds. This model is not suitable for human faces or human images.
* **Recommended LoRA scale:** 0.7 to 1.2
* **Color options:** You can add color specifications after the prompt, such as "**make it in embroidery style red and black colored**" or "**make it in embroidery style black and white colored**"
* **Input images:** High-resolution input images with limited color variety are recommended for best results
* **Note:** This is version 1 of the model and has some known limitations

## Training

#### Training Data
I trained the model on a custom dataset of paired (before and after) images to learn the "embroidery style" transformation. The model is specifically optimized for 2D drawings with solid backgrounds.

#### Training Procedure
I performed the training using the [FLUX Kontext Trainer on fal.ai](https://fal.ai/models/fal-ai/flux-kontext-trainer/playground).
The base model for training was `black-forest-labs/FLUX.1-Kontext-dev`.

**Hyperparameters:**
*   **Learning Rate:** 0.0001
*   **Steps:** 1300