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
Base Model recommendations
#58
pinned
by nphSi - opened
I usually do not use merges of distilled models because they always break loras but in this case i really can recommend such a merge. Its simple the best ZIT custom model i ever used aside original ZIT.
https://civitai.red/models/2562631/zit-zeus-darkmop-series?modelVersionId=3196453
Using it with res_multistep and beta or bong_tangent. (No AuraFlow needed. 8 Steps)
Remember, every time you change something in your workflow like sampler, lora or just weights you need to find a new "good" seed and keep that. How? Generate until you get a really bad image (body horror) and reroll the seed on that prompt until you get a fine image. Keep that seed.
nphSi pinned discussion