Instructions to use justinwlinx/ui-icon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use justinwlinx/ui-icon with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("justinwlinx/ui-icon", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
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.
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
- I'm a contributor to A1111, PixArt-alpha, Onediff
- More
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
- Downloads last month
- 3
Model tree for justinwlinx/ui-icon
Base model
lambda/miniSD-diffusers