---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- inference
widget:
- text: A photo of a woman in a floral dress
  output:
    url: images/2024-07-04_17-42-32_3003-enhanced (1).jpg
base_model: XLabs-AI/flux-RealismLora
instance_prompt: >-
  A high-resolution photo of a woman standing in a city street at night, wearing
  a floral dress
license: apache-2.0
---

# Keyli

This model, `Keyli`, is fine-tuned for generating high-quality images based on text prompts using the Stable Diffusion technique with LoRA (Low-Rank Adaptation). It leverages the `XLabs-AI/flux-RealismLora` as its base model, enabling it to produce realistic and detailed images.

## Model Overview

`Keyli` is designed for text-to-image generation tasks, and it performs particularly well in generating images of people in urban environments or similar settings. The model was fine-tuned with a focus on maintaining high realism and image quality.

<Gallery />

## Inference API

This model is compatible with the Hugging Face Inference API. You can use it directly in your applications to generate images from text descriptions. To do this, make sure the model is public and enabled for inference.

## Download Model

The weights for this model are available in Safetensors format.

[Download](/gerver/keyli/tree/main) the model files from the Files & versions tab.

## Example Usage

Here is how you can use this model with the `Diffusers` library:

```python
from diffusers import DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained("XLabs-AI/flux-RealismLora")
pipeline.load_lora_weights("gerver/keyli")

# Example prompt to generate an image
image = pipeline("A high-resolution photo of a woman standing in a city street at night, wearing a floral dress").images[0]
image.save("generated_image.png")