Instructions to use amd/HummingbirdXT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use amd/HummingbirdXT with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("amd/HummingbirdXT", 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
Comfy ui support?
#1
by ryg81 - opened
Comfy ui support?
the "inference code" is trying to load every model as if we are training the model , make it simple at least just the needed basic stuff with local model support if you are not going to add comfyui support.