---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
-   text: photograph of a small white toy poodle dressed as a fluffy ghost, complete
        with a flowing white sheet and playful eye holes, sitting among carved pumpkins
        and autumn leaves, with a mischievous sparkle in its eyes.festive atmosphere,
        spooky charm, vibrant colors, playful expressions, enchanting details, Halloween
        spirit Mini_HK
    output:
        url: samples/1729749023323__000001200_0.jpg
-   text: A charming photograph of a small white toy poodle dressed in a traditional
        Japanese kimono, sitting gracefully in a serene Kyoto garden, surrounded by
        blooming cherry blossoms and tranquil stone lanterns.Mini_HK
    output:
        url: samples/1729749054133__000001200_1.jpg
-   text: An elegant photograph of a small white toy poodle sitting regally on a plush
        velvet cushion, adorned with a tiny jeweled tiara and a luxurious collar,
        surrounded by soft, golden lighting that highlights its fluffy coat.Mini_HK
    output:
        url: samples/1729749084960__000001200_2.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Mini_HK
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
---

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

## Trigger words

You should use `Mini_HK` 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](/chau9ho/mini/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('chau9ho/mini', weight_name='mini.safetensors')
image = pipeline('photograph of a small white toy poodle dressed as a fluffy ghost, complete with a flowing white sheet and playful eye holes, sitting among carved pumpkins and autumn leaves, with a mischievous sparkle in its eyes.festive atmosphere, spooky charm, vibrant colors, playful expressions, enchanting details, Halloween spirit Mini_HK').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)