Instructions to use ostris/Flex.2-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/Flex.2-preview with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ostris/Flex.2-preview", 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
- Draw Things
- DiffusionBee
pipeline.to("cuda") is super slow
#20
by KnightOnLlama - opened
the loading to cpu phase is within one minute, but it takes ~20 min to run pipeline.to("cuda")
card: nvidia-H100-80g
anyone facing the same problem?