Instructions to use Te2douNin9/MOSS-Image-Kei with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Te2douNin9/MOSS-Image-Kei with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OpenMOSS-Team/MOSS-Image-Base", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Te2douNin9/MOSS-Image-Kei") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Improve the caption and training method
#1
by Te2douNin9 - opened
It's nice to announce that NOW you can load this LoRA alone WITHOUT aris lora to have right structrue of her halo.
Also, it's performance on expressing TendouKei's ringed eyes and halo:
All you need is to add words below into your prompt and click Generate:
"Inside each pink iris, draw exactly two separate, continuous, thin white circular outlines, concentric with the pupil. Keep both lines evenly spaced, uniform in thickness, and fully inside the iris. The iris has exactly two concentric outlines."
"A clearly visible pink geometric halo made of offset overlapping rectangular outlines floats above her head."
Te2douNin9 changed pull request status to merged