Instructions to use black-forest-labs/FLUX.1-Fill-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use black-forest-labs/FLUX.1-Fill-dev with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Fill-dev", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Diffusion Single File
How to use black-forest-labs/FLUX.1-Fill-dev with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Question about ae.safetensors and vae folder
#45
by cashtsangwh - opened
I wonder what is the difference between ae.safetensors and the vae folder? I try to load the vae and use :
vae = AutoencoderKL.from_single_file("./FLUX.1-Fill-dev/ae.safetensors", torch_dtype=torch.bfloat16)
It seems the architecture is not the same and error occur
But when I use vae = AutoencoderKL.from_pretrained("./FLUX.1-Fill-dev", subfolder='vae', torch_dtype=torch.bfloat16), it was loaded successfully.
In many Comfyui cases, I see many people use ae.safetensors instead of the vae file provided in Flux, I don't know what is the difference and why it is existed in the repository, what is its usage?