---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
-   text: an animated man in a blue hoodie holding a sword, standing in front of a
        wall with various objects in the background. [trigger]
    output:
        url: samples/1736414052380__000001000_0.jpg
-   text: an animated person holding a glowing object in their hand, with another
        person in the background. The person on the right side of the image is wearing
        a blue and white outfit, and the object they are holding appears to be a character
        from the anime series Yu-Gi-Oh! Duel Monsters. [trigger]
    output:
        url: samples/1736414082493__000001000_1.jpg
-   text: 'a poster featuring animated characters from the game The Legend of Heroes:
        Trails of Cold Steel III. The poster has text written on it, likely describing
        the game and its characters. [trigger]'
    output:
        url: samples/1736414112528__000001000_2.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: fantasy
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---

# myt-flux-fantasy

<Gallery />

## Trigger words

You should use `fantasy` 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](/openfree/myt-flux-fantasy/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-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('openfree/myt-flux-fantasy', weight_name='myt-flux-fantasy.safetensors')
image = pipeline('an animated man in a blue hoodie holding a sword, standing in front of a wall with various objects in the background. [trigger]').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)