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
Request / Suggest a Lora
You can request as much Loras you like but there is no guarantee i create them even if you supported me on Ko-FI.com.
- Currently accepted: Z-Image.
- Priority of Requests/Suggestions, Number of new Loras and update frequency is directly related to the amount of support i receive via ko-fi.com
- I may fulfil requests more quickly if i am personally interested. ko-fi.com can raise my interest!
- Well known Characters only. No Influencers or TikTok/OnlyFans/Adult models or Pornstars etc. This belongs to B-Sides (see forum post) and requires support via ko-fi.com (see above).
- B-Sides must have enough normal real world SFW (Clothed/Bikini) images available. I do not train pornographic content!
- If you requests B-Sides here please add your ko-fi username you used to support me.
- About requests for a specific Era or themed Lora:
The most important thing about making a good working Lora is absolute highest quality and diversity in the dataset. Being stuck in a tight time frame with analogue magazine scans
makes it impossible. Such a Lora would be highly inflexible and from bad overall quality. See Ornella Muti or Cybill Shepherd Loras for example. They are made exclusively with old
analogue photo scans. Another example is Stephanie Meissner, made out of a few 720p Youtube clips. My goal is always to reflect people when they where at their prime time while
matching the image we have memorised them as close as possible.
The major criteria for Loras in the main list is broad mainstream popularity and availability of good quality and diverse images on free and public accessible sites.
No Supermodels, "Miss Whatever" or anyone whos main business is being photographed. Exception are (Ex) Supermodels who turned actor etc.
Before requesting/suggesting a Lora please do yourself a basic check for available images for a dataset. Check listal.com and wikifeet.com . If you do not find some images there a Lora is probably not possible at all.
If you have already collected images usable for a dataset please provide a download url.I will silently ignore all entries from people who clearly did not read this post.
π§ = Training
β = Finished
π = On hold (few/bad images)
Molly Caudery (Athlete)
Ellyse Perry (Athlete)
Eileen Gu (Athlete)
Ana Maria MarkoviΔ (Soccer)
Jordyn Huitema (Soccer)
Julia Beautx (Actress)
Eugenie Bouchard (Tennis)
Jesy Nelson
Hannah Dodd
Florence Hunt
Claudia Jessie
Ruth Gemmell
Yerin Ha
I just found out you did LoRas of Lena Paul and HoneyPuu, is there any chance of seeing more a. actresses and streamers?
(removed list)
π Edit (nphSi): No. Lena Paul and HoneyPuu was kind of a test. Result is: It is much too time-consuming to find normal SFW images usable for a dataset.
Melanie Vallejo
Meghann Fahy would be much appreciated.
https://www.harpersbazaar.com/celebrity/latest/a43684908/meghann-fahy-bikini-top-flared-pants-fashion-awards-red-carpet/
can you train
Michelle Pfeiffer
Julia Roberts
Susan Sarandon
Jodie Foster
when they were younger
thanks .
π Edit (nphSi): They are all on my list since a long time but i successfully dodged them because datasets require much more work. I try to do a few in the next time...