Instructions to use blurgy/CoMPaSS-FLUX.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use blurgy/CoMPaSS-FLUX.1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("blurgy/CoMPaSS-FLUX.1") prompt = "a photo of a laptop above a dog" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
SDXL version? ππΎ
#3
by RamonGuthrie - opened
Can we have a SDXL version? ππΎ
Hi @RamonGuthrie , thanks for the great suggestion.
While I don't have immediate plans to train an SDXL version myself due to other commitments, our research indicates that SDXL would be a prime candidate and should benefit significantly from our approach.
I've written a more detailed technical explanation on how this could be done by the community in a GitHub issue. You can find the full details here: https://github.com/blurgyy/CoMPaSS/issues/5
I'm leaving that issue open to encourage community contributions and would be happy to review a pull request if someone decides to take it on.
Thanks again for your interest!