---
license: openrail++
tags:
- text-to-image
- stable-diffusion
---

![image/gif](https://cdn-uploads.huggingface.co/production/uploads/637a6daf7ce76c3b83497ea2/ux_sZKB9snVPsKRT1TzfG.gif)

<hr>

# Overview
SDXL-512 is a checkpoint fine-tuned from SDXL 1.0 that is designed to generate higher-fidelity images at and around the 512x512 resolution. The model has been fine-tuned using a learning rate of 1e-6 over 7000 steps with a batch size of 64 on a curated dataset of multiple aspect ratios. alternating low and high resolution batches (per aspect ratio) so as not to impair the base model's existing performance at higher resolution.
- **Use it with [Hotshot-XL](https://huggingface.co/hotshotco/Hotshot-XL) (recommended)**

<hr>

# Model Description
- **Developed by**: Natural Synthetics Inc.
- **Model type**: Diffusion-based text-to-image generative model
- **License**: CreativeML Open RAIL++-M License
- **Model Description**: This is a model that can be used to generate and modify higher-fidelity images at and around the 512x512 resolution.
- **Resources for more information**: Check out our [GitHub Repository](https://github.com/hotshotco/hotshot-xl).
- **Finetuned from model**: [Stable Diffusion XL 1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)

<hr>

# 🧨 Diffusers 

Make sure to upgrade diffusers to >= 0.18.2:
```
pip install diffusers --upgrade
```

In addition make sure to install `transformers`, `safetensors`, `accelerate` as well as the invisible watermark:
```
pip install invisible_watermark transformers accelerate safetensors
```

Running the pipeline (if you don't swap the scheduler it will run with the default **EulerDiscreteScheduler** in this example we are swapping it to **EulerAncestralDiscreteScheduler**:
```py
import torch
from torch import autocast
from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
model = "hotshotco/SDXL-512"
pipe = StableDiffusionXLPipeline.from_pretrained(
    model, 
    torch_dtype=torch.float16, 
    use_safetensors=True, 
    variant="fp16"
    )
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.to('cuda')
prompt = "a woman laughing"
negative_prompt = ""
image = pipe(
    prompt, 
    negative_prompt=negative_prompt, 
    width=512,
    height=512,
    guidance_scale=12,
    target_size=(1024,1024),
    original_size=(4096,4096),
    num_inference_steps=50
    ).images[0]
image.save("woman_laughing.png")
```

<hr>

# Limitations and Bias
## Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.

## Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.