Instructions to use lodestones/Chroma1-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lodestones/Chroma1-Flash 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-Flash", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Chroma-*.safetensors v. Chroma1-*.safetensors
#1
by jurassicstrain - opened
This is a minor thing, but on your different repos you use Chroma1-HD-Flash, Chroma-HD-Annealed/Chroma-HD, and Chroma for the .safetensors files but the repos are called Chroma1-Flash, Chroma1-HD, and Chroma1-Base, respectively (plus the original Chroma repo for the iterations). I'm not sure if this one deliberately includes the "1" and/or the "HD", but it would probably be good to have a consistent naming convention for the various model files.
Or even just a small comment that says what the model is. Like "This model is a low-step version of... Recommend CFG X and number steps Y." A lot of work was put into this model but we would all be thankful for a little help using it.