Instructions to use Omnico/Chroma1_diff_loras with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Omnico/Chroma1_diff_loras with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lodestones/Chroma1-Base", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Omnico/Chroma1_diff_loras") prompt = "real photo, amateur photo, " image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
About using these loras
#1
by Not-your-Tim - opened
First of all, thank you for your work. I was wondering, if I understood correctly, the idea is using these loras with the base chromahd model?
First of all, thank you for your work. I was wondering, if I understood correctly, the idea is using these loras with the base chromahd model?
Yes
Yes, you can use BASE, HD, or an earlier version of Chroma1 with these LoRAs, and everything should work. Except for the Turbo version (this was an initially unsuccessful model; nothing was tested with it, and some of the extracted LoRAs already contain some accelerators to reduce steps, so there may be a conflict).