Instructions to use rain1011/pyramid-flow-sd3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use rain1011/pyramid-flow-sd3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("rain1011/pyramid-flow-sd3", 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
MacOS support
#18
by maximo10 - opened
does it support mps instead of Cuda ?
I'm still desperately trying but no luck so far. I needed to boot comfy ui with PYTORCH_ENABLE_MPS_FALLBACK=1 but even then I still keep getting the error message "TypeError: Cannot convert a MPS Tensor to float64 dtype as the MPS framework doesn't support float64. Please use float32 instead." with any of the provided model dtypes (fp8, fp32, fp16, bf 16). None of these is supposed to be fp64 anyway so I'm not sure where the error message comes from