| --- |
| license: creativeml-openrail-m |
| base_model: "lambdalabs/miniSD-diffusers" |
| dataset: LAION Improved Aesthetics 6plus |
| tags: |
| - stable-diffusion-14 |
| - stable-diffusion-14-diffusers |
| - text-to-image |
| - diffusers |
| - miniSD |
| - ui |
| - icons |
| - logo |
| - symbol |
| - mark |
| inference: true |
| --- |
| |
| SOTA model for generating icons. |
|
|
| Motivation: |
| I spent $2000 of my own money to train this model. I was unable to monetize it, so I'm sharing it with others. |
| <img src="https://avatars.githubusercontent.com/u/95939477?s=200&v=4" width="60"/> Train on Runpod. |
|
|
| Trained on MiniSD. |
|
|
| Want to collaborate on open source together with me? Send me a message: kopyloleh@gmail.com / telegram @kopyl |
|
|
| Check my other cool projects: |
| - [Logo generator](https://logojinn.com/) |
| - I'm a contributor to [A1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui), [PixArt-alpha](https://github.com/PixArt-alpha/PixArt-alpha), [Onediff](https://github.com/siliconflow/onediff) |
| - [More](https://kopyloleh.com/) |
|
|
|
|
| Check some cool images i was able to generate with this model. |
|  |
|  |
|  |
|  |
| More cherry-picked generated images: https://t.me/s/sdicon . |
| Or generate your own via a free Telegram bot: https://t.me/aiiconbot . |
|
|
|
|
| I'd love if you could use it in your app and let me know. |
| Also not mandatory, but i'd appreciate if you could attribute me to it by putting my website https://kopyloleh.com/ . |
|
|
| This model is only able to generate images in 256x256px size, so you need to use some upscaler. I use Real ESRGAN, but you could also try SUPIR. |
|
|
| All prompts have to end with " icon". Meaning: |
| - lion icon |
| - snowman icon |
|
|
| You can find the AUTOMATIC1111 WebUI checkpoint here: https://civitai.com/models/327499/ui-icons |
