Instructions to use XLabs-AI/flux-ip-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use XLabs-AI/flux-ip-adapter with Diffusers:
pip install -U diffusers transformers accelerate
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline controlnet = ControlNetModel.from_pretrained("XLabs-AI/flux-ip-adapter") pipe = StableDiffusionControlNetPipeline.from_pretrained( "fill-in-base-model", controlnet=controlnet ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Xlabs Sampler CUDA Only
#9
by 21machines - opened
Too bad I can't run any of these fine Xlabs workflows. "Torch not compiled with CUDA enabled". I quietly mutter something about Tim Apple.
Hi! Could you please add info about your CUDA, torch version, device etc?
No need, I'm on a MPS macOS 96GB, 38-core GPU - Mac Studio. Anything Xlabs does with the Xlabs Sampler in the workflow throws this CUDA error. I don't expect you to build a none CUDA version. But, I did want to say thank you so much for the support you are showing the open source community!