README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- diffusers-training
- flux
widget:
- text: >-
    This set of four image depicts a cartoon black cat wearing a pirate hat;
    [IMAGE1] The cat is happy, holding a bouquet; [IMAGE2] The cat is happy,
    surrounded with music notes; [IMAGE3] The cat is riding a bicycle; [IMAGE4]
    The cat is eating an ice cream
  output:
    url: images/img_483760_0.png
- text: >-
    This set of four image depicts a cartoon corgi; [IMAGE1] The corgi is happy,
    eating from a bowl; [IMAGE2] The corgi is sad, crying; [IMAGE3] The corgi is
    playing with a ball; [IMAGE4] The corgi is in neutral state
  output:
    url: images/img_941190_3.png
- text: >-
    This set of four image depicts a cartoon hamster; [IMAGE1] The hamster is
    happy, holding a game controller; [IMAGE2] The hamster is sad, crying;
    [IMAGE3] The hamster is holding a white board with text 'NO'; [IMAGE4] The
    hamster is in neutral state
  output:
    url: images/img_982953_3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: >-
  This set of four image depicts a cartoon <subject>; [IMAGE1]; [IMAGE2];
  [IMAGE3]; [IMAGE4]
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
---
# In Context 4x4 Sticker sheet

<Gallery />

## Model description

These are DreamBooth LoRA weights for black-forest-labs/FLUX.1-dev.

The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [Flux diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md).

Was LoRA for the text encoder enabled? False.

Pivotal tuning was enabled: False.

## 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('rootonchair/4x4_sticker_sheet', weight_name='pytorch_lora_weights.safetensors', adapter_name='4x4_sticker_sheet')
pipeline.set_adapters(['4x4_sticker_sheet'], adapter_weights=[0.8])

image = pipeline('This set of four image depicts a cartoon black cat wearing a pirate hat; [IMAGE1] The cat is happy, holding a bouquet; [IMAGE2] The cat is happy, surrounded with music notes; [IMAGE3] The cat is riding a bicycle; [IMAGE4] The cat is eating an ice cream', width=512, height=512, num_inference_steps=28, guidance_scale=3.5).images[0]
```

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)

## License

Please adhere to the licensing terms as described [here](https://huggingface.co./black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).

## Trigger words

You should use `This set of four image depicts a cartoon <subject>; [IMAGE1]; [IMAGE2]; [IMAGE3]; [IMAGE4]` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/rootonchair/4x4_sticker_sheet/tree/main) them in the Files & versions tab.