Instructions to use Onodofthenorth/SD_PixelArt_SpriteSheet_Generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Onodofthenorth/SD_PixelArt_SpriteSheet_Generator with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Onodofthenorth/SD_PixelArt_SpriteSheet_Generator", torch_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 Settings
- Draw Things
- DiffusionBee
Checkpoint Question
#7
by fwmeokok - opened
This model is impressive, especially given SD's current limitations. My question is this: can I simply replace my current model's ckpt with the PixelartSpritesheet_V.1.ckpt ?
If so, is that the only step I would have to take to achieve the results you've produced here?
Thanks
Yeah, that’s pretty much it! Make sure to use the keywords described in the model card. I like to scale the output down and then back up again using nearest-neighbor scaling. This usually helps to clean up color bleed. Good luck and let me know how it goes or if you have any other questions.
Onodofthenorth changed discussion status to closed