Instructions to use imperatrona/flux-dev-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use imperatrona/flux-dev-fp8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("imperatrona/flux-dev-fp8", 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 Settings
- Draw Things
- DiffusionBee
Errors while loading model with Diffusers
Hi,
I'm trying to load the model with diffusers, with FluxPipeline.from_pretrained, and got some errors.
The first error was from the vae, when the config file name of the vae is vae_config.jason instead of config.json. So I renamed it locally.
The second error was for the tokenizer(which I didn't solve yet):
raise EnvironmentError(
OSError: Can't load tokenizer for '/root/.cache/huggingface/hub/models--imperatrona--flux-dev-fp8/snapshots/76e81036db0f0722cc03d1a21fbe4dbd7252d76e/tokenizer'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure '/root/.cache/huggingface/hub/models--imperatrona--flux-dev-fp8/snapshots/76e81036db0f0722cc03d1a21fbe4dbd7252d76e/tokenizer' is the correct path to a directory containing all relevant files for a CLIPTokenizer tokenizer.