Text-to-Image
Diffusers
lora
ernie
image-generation
anime
illustration
flat-style
vector-art
cel-shading
stylization
character-design
Instructions to use HexDuck/FMIX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use HexDuck/FMIX with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("baidu/ERNIE-Image", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("HexDuck/FMIX") prompt = "Fimix:, a highly energetic magical girl with twirling pink pigtails, shouting happily while swinging a glowing star-topped wand, wearing a frilly cosmic-themed dress with floating ribbons, casting a massive bright neon spell that materializes the word \"FMix\" in glowing solid magical energy, a vibrant abstract dimension of shooting stars and geometric auroras, dynamic low angle shot, intensely bright magical rim lighting casting sharp cell-shaded shadows, explosive and magical atmosphere, premium flat style aesthetic, flat colors background, vector art style background, cell shading" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee