Instructions to use nerijs/pixel-art-medium-128-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nerijs/pixel-art-medium-128-v0.1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("nerijs/pixel-art-medium-128-v0.1") prompt = "portrait of a cute happy corgi wearing a party hat, pastel color background, pixel art style" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Pixel Art Medium 128 v0.1
.png)
- Prompt
- portrait of a cute happy corgi wearing a party hat, pastel color background, pixel art style
- Negative Prompt
- realistic, 3d render, photo

- Prompt
- portrait of a cute happy corgi wearing a party hat, pastel color background, pixel art style
- Negative Prompt
- realistic, 3d render, photo
Model description
This is an early version of "Pixel Art Medium" for SD3 Medium. Outputs 128x128 pixel art, grid-aligned images.
Tips
- Always use "pixel art style" at the end of the prompt
- Use "realistic, 3d render, photo" as the negative prompt to get better results
- Add "flat, simple colors" to the prompt for better styling
- Sample images generated using the default Diffusers pipeline at 1.0 strength, default sampler, 28 steps and CFG of 5.0
Only tested on Diffusers, Comfy support needs to be tested
Trigger words
You should use pixel art style to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
How to use
- Downloads last month
- 54
