Instructions to use fal/AuraFlow with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fal/AuraFlow with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fal/AuraFlow", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
error with Bias term
#18
by kppp199 - opened
got the following error when trying to run the model through diffusers 0.30.dev0
File "/usr/local/lib/python3.8/dist-packages/diffusers/models/transformers/auraflow_transformer_2d.py", line 179, in init
self.norm1 = AdaLayerNormZero(dim, bias=False, norm_type="fp32_layer_norm")
File "/usr/local/lib/python3.8/dist-packages/diffusers/models/normalization.py", line 87, in init
self.norm = FP32LayerNorm(embedding_dim, elementwise_affine=False, bias=False)
it seems like the line 87 of normalization.py is having an unrecognized parameter
Please upgrade your torch version to 2.1 or above. It should fix this.