---
base_model: black-forest-labs/FLUX.1-schnell
license: apache-2.0
tags:
- autotrain
- spacerunner
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
widget:
- text: A person in a bustling cafe in the style of Zeyan
  output:
    url: samples/1725700482960__000001500_0.jpg
- text: A person playing football in the style of Zeyan
  output:
    url: samples/1725700500410__000001500_1.jpg
- text: A person celebrating birthday in the style of Zeyan
  output:
    url: samples/1725700517623__000001500_2.jpg
- text: Superman celebrating birthday in the style of Zeyan
  output:
    url: images/example_ydev0uaqs.png
- text: >-
    Superman hovers majestically above a sprawling metropolis, his iconic red
    cape billowing dramatically in the wind. Below, the city glistens with
    towering skyscrapers and glowing lights as dusk settles in, casting long
    shadows and a golden hue over the horizon. The perspective is cinematic,
    with Superman in the foreground, his muscular frame exuding strength and
    heroism. His eyes are set with determination, and his posture embodies the
    weight of responsibility he carries. The sky behind him is stormy, blending
    blues and grays, adding an epic, larger-than-life feel. In the style of
    Zeyan
  output:
    url: images/example_yb8yv6x77.png
instance_prompt: in the style of Zeyan

---

# zeyan-lora
Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
<Gallery />

## Trigger words

You should use `in the style of Zeyan` to trigger the image generation.

## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.

Weights for this model are available in Safetensors format.

[Download](/liuhahi/zeyan-lora/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-schnell', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('liuhahi/zeyan-lora', weight_name='zeyan-lora')
image = pipeline('A person in a bustling cafe in the style of Zeyan').images[0]
image.save("my_image.png")
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co./docs/diffusers/main/en/using-diffusers/loading_adapters)