Instructions to use nphSi/Z-Image-Lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nphSi/Z-Image-Lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Tongyi-MAI/Z-Image,Tongyi-MAI/Z-Image-Turbo", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("nphSi/Z-Image-Lora") prompt = "Alexandra Chando (vrtlAlexandraChando)" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Wishlist for training existing dataset on krea.2 RAW 512px
#55
pinned
by nphSi - opened
I can train some selected lookalikes on krea2. Training on krea2 is easy they say but creating a good dataset is not. Add a name,
- must be mostly unknown to krea2 RAW. Please do some tests before.
- you must have supported me at least once on ko-fi
- one entry per person
- lookalike must have an ZI Lora here already (a dataset).
After we reach lets say 10 names ill start a vote on Ko-Fi and train the 3 most voted.
We repeat if it worked out well...
nphSi pinned discussion
Sydney Sweeney
Sadie Sink
Anna Cramling
Brooke Monk