---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
-   text: Rust-eaten locomotives slump in a valley swallowed by wildflowers and thorny
        brambles, their shattered windows glittering like jagged teeth under a stormy
        violet sky. Vines snake through coal carriages, while a lone fox pauses on
        tracks buried under dandelions. Lightning fractures the horizon, illuminating
        graffiti ghosts of names long forgotten. Ruin5
    output:
        url: samples/1744049483171__000004000_0.jpg
-   text: A cathedral-like library collapses under centuries of rot, its sagging shelves
        spilling leather-bound tomes into pools of rainwater and glowing bioluminescent
        fungi. Moonbeams slice through holes in the vaulted ceiling, catching motes
        of dust and the faint etchings of arcane symbols on crumbling pillars. A moth-eaten
        tapestry flaps in the wind, its embroidered prophecies half-eaten by time.
        Ruin5
    output:
        url: samples/1744049524102__000004000_1.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Ruin5
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
---

# Ruins_v1
Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit)
<Gallery />

## Trigger words

You should use `Ruin5` 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](/ayanda13/Ruins_v1/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('ayanda13/Ruins_v1', weight_name='Ruins_v1.safetensors')
image = pipeline('Rust-eaten locomotives slump in a valley swallowed by wildflowers and thorny brambles, their shattered windows glittering like jagged teeth under a stormy violet sky. Vines snake through coal carriages, while a lone fox pauses on tracks buried under dandelions. Lightning fractures the horizon, illuminating graffiti ghosts of names long forgotten. Ruin5').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)