---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
-   text: A playful photograph of a black dog dressed as a spooky vampire, complete
        with a tiny cape and playful fangs, sitting on a rocky outcrop under a full
        moon, surrounded by glowing jack-o'-lanterns and fluttering bats,festive atmosphere,
        whimsical details, vibrant colors, Halloween spirit, playful expression, enchanting
        nighttime setting, Somie_HK
    output:
        url: samples/1729753267982__000001200_0.jpg
-   text: A vibrant photograph of a black dog wearing a colorful hiking harness, confidently
        perched on a rocky ledge, overlooking a breathtaking mountain vista filled
        with lush greenery and clear blue skies. adventurous spirit, nature vibes,
        dynamic pose, bright colors, outdoor exploration, joyful expression, scenic
        beauty, Somie_HK
    output:
        url: samples/1729753298821__000001200_1.jpg
-   text: A stunning art painting of a black dog sitting majestically against a backdrop
        of soft, impressionistic landscapes, with gentle brush strokes highlighting
        the dog's shiny coat and expressive eyes, evoking a sense of warmth and companionship,
        artistic flair, rich textures, warm tones, emotional depth, timeless beauty,
        whimsical charm, evocative imagery, Somie_HK
    output:
        url: samples/1729753329636__000001200_2.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Somie_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
---

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

## Trigger words

You should use `Somie_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/somie/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/somie', weight_name='somie.safetensors')
image = pipeline('A playful photograph of a black dog dressed as a spooky vampire, complete with a tiny cape and playful fangs, sitting on a rocky outcrop under a full moon, surrounded by glowing jack-o'-lanterns and fluttering bats,festive atmosphere, whimsical details, vibrant colors, Halloween spirit, playful expression, enchanting nighttime setting, Somie_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)