---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
-   text: A sophisticated toy poodle with apricot-colored fur, expertly groomed into
        a round teddy bear cut, wearing a lime green silk bow tie, lounging in a French
        garden conservatory, soft bokeh background with blooming blue hydrangeas,
        professional portrait lighting, shallow depth of field, shot on Canon EOS
        R5, marbles_hk
    output:
        url: samples/1729837920462__000001200_0.jpg
-   text: Whimsical portrait of a miniature poodle as a Victorian aristocrat, fluffy
        cream-colored coat perfectly styled, emerald silk bow at neck, reclining on
        a velvet fainting couch, surrounded by English cottage garden flowers, dreamy
        afternoon light, studio photography, f/2.8 aperture, marbles_hk
    output:
        url: samples/1729837951296__000001200_1.jpg
-   text: 'High-fashion pet editorial: caramel-toned toy poodle with cloud-like fur
        texture, sporting a spring green designer bow, posed against an impressionist
        garden backdrop, blue hydrangeas adding pop of color, soft natural lighting
        with gentle shadows, magazine-style composition, shot on medium format digital,
        marbles_hk'
    output:
        url: samples/1729837982097__000001200_2.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: marbles_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
---

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

## Trigger words

You should use `marbles_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/marbles/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/marbles', weight_name='marbles.safetensors')
image = pipeline('A sophisticated toy poodle with apricot-colored fur, expertly groomed into a round teddy bear cut, wearing a lime green silk bow tie, lounging in a French garden conservatory, soft bokeh background with blooming blue hydrangeas, professional portrait lighting, shallow depth of field, shot on Canon EOS R5, marbles_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)