---
language:
- en
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- art
- artistic
- diffusers
- cs:go
- topview
- map generator
- layout
- layout generator
- map
- csgo
- improved layout
- radar
inference: true
license: creativeml-openrail-m
---

# CSGO Minimap Layout Generation

![img](https://huggingface.co/Kaludi/CSGO-Minimap-Layout-Generation/resolve/main/csgoMiniMapLayoutsV2.png)

This is an improved AI model of my previous model trained on CS:GO's radar top view images of many maps which can now  produce custom map layouts in seconds. This model does not produce red or green boxes like in my previous model. The tag for this model is  **"radar-topview"**. If you'd like to get a map layout similar to a specific map, you can add the map name before "radar-topview". So if I wanted a map generation similar to dust2, I would write  **"dust2-radar-topview"**.

**Try the following prompt to get the best results:**  
"fps radar-topview game map, flat shading, soft shadows, global illumination"  
"fps radar topview map, polygonal, gradient background, pastel colors, soft shadows, global illumination, straight lines, insanely detailed"

**Map Radar Topviews this AI was trained on:**  
de_dust2
de_inferno
de_nuke
de_mirage
de_cache
de_train
de_cobblestone
de_castle
de_overpass

**Have fun generating map layouts!**

### CompVis

[Download csgoTopViewMapLayout.ckpt) (2.9GB)](https://huggingface.co/Kaludi/CSGO-Minimap-Layout-Generation/blob/main/csgoMiniMapLayoutsV2.ckpt)

### 🧨 Diffusers

This model can be used just like any other Stable Diffusion model. For more information,
please have a look at the [Stable Diffusion Pipeline](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).

```python
from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler
import torch

prompt = (
"fps radar-topview game map, flat shading, soft shadows, global illumination")

model_id = "Kaludi/CSGO-Improved-Radar-Top-View-Map-Layouts"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")

image = pipe(prompt, num_inference_steps=30).images[0]

image.save("./result.jpg")
```

## License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
The CreativeML OpenRAIL License specifies: 

1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content 
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
[Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)