Instructions to use Fazzie/PokemonGAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Fazzie/PokemonGAI with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Fazzie/PokemonGAI", dtype=torch.bfloat16, device_map="cuda") prompt = "dragon armored (eevee), wings, (fire claws), smoke, cityscape" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
My kids love this. Stable Diffusion 2.1 model trained, via Dreambooth, for generations 1-8 of Pokemon "Sugimori" designs. 768x768 for best results. Good for mixing species and types, adequate at applying species and types to non-pokemon terms (like fire horse).
Added terms include GMAX, Mega, (PokemonName), (PokemonType). GMAX works well as a style. Recommend adding "mega" and "gmax" to negative prompt unless you're into that.
Prompt: dragon armored (eevee), wings, (fire claws), smoke, cityscape
Negative: pixelated, distorted
Prompt: fire greninja, wings, (fire claws), smoke, cityscape
Negative: pixelated, distorted
Prompt: mega nidoqueen, purple smoke, cityscape
Negative: pixelated, distorted

- Downloads last month
- 12