---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
-   text: a group of three women and a man standing next to each other in front of
        a boat. The man is wearing a white and pink dress, while the two women are
        wearing pink dresses. The woman on the right is wearing black goggles, and
        the background is illuminated by a few lights. This image is reminiscent of
        the iconic 80s movie, Dirty Dancing. retromiami
    output:
        url: samples/1731077976325__000001000_0.jpg
-   text: a woman sitting at a bar with wine glasses in front of her, illuminated
        by the lights in the background. She is wearing a glamorous outfit and has
        a confident expression on her face, as if she is ready to take on the world.
        retromiami
    output:
        url: samples/1731077992608__000001000_1.jpg
-   text: two women wearing sunglasses sitting next to each other in front of a palm
        tree. They are both wearing white and blue dresses and one of them is wearing
        a necklace. The background is slightly blurred, giving the image a dreamy
        feel. retromiami
    output:
        url: samples/1731078008904__000001000_2.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: retromiami
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
---

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

## Trigger words

You should use `retromiami` 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](/life/retromiami/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('life/retromiami', weight_name='retromiami.safetensors')
image = pipeline('a group of three women and a man standing next to each other in front of a boat. The man is wearing a white and pink dress, while the two women are wearing pink dresses. The woman on the right is wearing black goggles, and the background is illuminated by a few lights. This image is reminiscent of the iconic 80s movie, Dirty Dancing. retromiami').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)