---
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
-   text: '[trigger] ADscenario describing a left turn intersection. The ego vehicle
        wants to turn left'
    output:
        url: samples/1749822270115__000002000_0.jpg
-   text: '[trigger] ADscenario describing a driving maneuver on highway. The ego
        vehicle drives behind a front vehicle on the right lane on the highway'
    output:
        url: samples/1749822279237__000002000_1.jpg
-   text: '[trigger] ADscenario describing a an evasion maneuver. The ego vehicle
        change the lane in urban environment'
    output:
        url: samples/1749822288385__000002000_2.jpg
-   text: '[trigger] ADscenario describing a driving situation in a construction site.
        The ego vehicle drives between cones'
    output:
        url: samples/1749822297518__000002000_3.jpg
-   text: '[trigger] ADscenario describing a traffic light driving situation. The
        ego vehicle stops for a red light'
    output:
        url: samples/1749822306643__000002000_4.jpg
base_model: black-forest-labs/FLUX.1-schnell
instance_prompt: ADscenario
license: apache-2.0


---

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

## Trigger words

You should use `ADscenario` 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](/TFree2035/FluxScenario2/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-schnell', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('TFree2035/FluxScenario2', weight_name='loraSayed.safetensors')
image = pipeline('[trigger] ADscenario describing a left turn intersection. The ego vehicle wants to turn left').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)