---
license: apache-2.0
pipeline_tag: text-to-image
---

# Controlling Structure and Appearance for SSD-1B

The CtrlXStableDiffusionXLPipeline has been modified, since it had way too much TODO lines. Refiner phase is removed.

Requires 8GB VRAM.

## Setup

```
pip install accelerate diffusers gradio torch safetensors transformers
```

## Inference

```python
python run_ctrlx.py --num_inference_steps 20 --guidance_scale 9.0 --model_offload --structure_image images_ctrlx/horse__point_cloud.jpg --appearance_image images_ctrlx/horse.jpg --prompt "a photo of a horse standing on grass" --structure_prompt "3D point cloud of a horse"
```

## Disclaimer

All code belongs to [Jordan Lin](https://github.com/genforce/ctrl-x), the models weight to [Segmind](https://huggingface.co/segmind/SSD-1B).