---
license: apache-2.0
language:
- en
base_model:
- black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
tags:
- lora
- flux
- flux-dev
- realism
- character
- portrait
library_name: diffusers
---
## LORA FLUX.1-dev example

Lora for [FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev)

**valentin** trigger word required

## 🌟 About FlyMy.AI

Agentic Infra for GenAI. FlyMy.AI is a B2B infrastructure for building and running GenAI Media agents.

**🔗 Useful Links:**
- 🌐 [Official Website](https://flymy.ai)
- 📚 [Documentation](https://docs.flymy.ai/intro)
- 💬 [Discord Community](https://discord.com/invite/t6hPBpSebw)
- 🤗 [LoRA Training Repository](https://github.com/FlyMyAI/flymyai-lora-trainer)
- 🐦 [X (Twitter)](https://x.com/flymyai)
- 💼 [LinkedIn](https://linkedin.com/company/flymyai)
- 📺 [YouTube](https://youtube.com/@flymyai)
- 📸 [Instagram](https://www.instagram.com/flymy_ai)

# 🧪 Usage
---
### 🔧 Initialization

```python
from diffusers import DiffusionPipeline
import torch

model_name = "black-forest-labs/FLUX.1-dev"

# Load the pipeline
if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"

pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch_dtype)
pipe = pipe.to(device)
```

### 🔌 Load LoRA Weights

```python
# Load LoRA weights
pipe.load_lora_weights('character_lora.safetensors', adapter_name="lora")
```

### 🎨 Generate Image with lora trained on person

```python
prompt = '''valentin sitting on a chair, portrait'''
negative_prompt = "blurry, low quality, distorted, bad anatomy"
image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=1024,
    height=1024,
    num_inference_steps=28,
    guidance_scale=3.5,
    generator=torch.Generator(device="cuda").manual_seed(42)
).images[0]

# Display the image (in Jupyter or save to file)
image.show()
# or
image.save("output.png")
```

### 🖼️ Sample Output

![Sample Output](./assets/generations/gen2.jpg)

### Workflow Features

- ✅ Pre-configured for FLUX.1-dev + LoRA inference
- ✅ Optimized settings for best quality output
- ✅ Easy prompt and parameter adjustment
- ✅ Compatible with all our trained LoRA models

The ComfyUI workflow provides a user-friendly interface for generating images with our trained LoRA models without needing to write Python code.

### 🖼️ Workflow Screenshot

![ComfyUI Workflow](./assets/comfyui_workflow.png)

## 🎨 Generation Examples

Below are examples of images generated with our Valentin LoRA model:

### Official Style Portrait

**Prompt**: *"valentin official style portrait"*

![Official Style Portrait](./assets/generations/gen1.jpg)

### Cyberpunk Close-up

**Prompt**: *"valentin close up in a cyberpunk aesthetic, neon lighting, holographic elements, wearing futuristic clothing, standing in a neon-lit alley, sci-fi atmosphere, digital art"*

![Cyberpunk Close-up](./assets/generations/gen3.jpg)

### Greek City Portrait

**Prompt**: *"valentin wearing sunglasses and a hat in a Greek city"*

![Greek City Portrait](./assets/generations/gen5.jpg)

### Fluorescent Garden Editorial

**Prompt**: *"valentin, waist-up, standing in a fluorescent garden under blacklight, glowing bioluminescent plants, saturated purple and green hues, reflective sunglasses catching UV glints, surreal fashion editorial aesthetic, hyperreal depth, cinematic 85mm photography"*

![Fluorescent Garden Editorial](./assets/generations/gen7.jpg)

## 🚀 Try it Online

Test this LoRA model directly in your browser:
- 🌐 [Try on FlyMy.AI Platform](https://app.flymy.ai/models/flymyai/flux-lora-trainer-fast)

## 🤝 Support

If you have questions or suggestions, join our community:
- 🌐 [FlyMy.AI](https://flymy.ai)
- 📚 [Documentation](https://docs.flymy.ai)
- 💻 [GitHub](https://github.com/flymy-ai)
- 💬 [Discord Community](https://discord.com/invite/t6hPBpSebw)
- 🐦 [Follow us on X](https://x.com/flymyai)
- 💼 [Connect on LinkedIn](https://linkedin.com/company/flymyai)
- 📧 [Support](mailto:support@flymy.ai)

**⭐ Don't forget to star the repository if you like it!**

---
license: apache-2.0
---