Instructions to use CutePickle/FLUX.1-Fill-dev-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use CutePickle/FLUX.1-Fill-dev-nf4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import FluxFillPipeline from diffusers.utils import load_image image = load_image("https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/cup.png") mask = load_image("https://huggingface.co/datasets/diffusers/diffusers-images-docs/resolve/main/cup_mask.png") # switch to "mps" for apple devices pipe = FluxFillPipeline.from_pretrained("CutePickle/FLUX.1-Fill-dev-nf4", dtype=torch.bfloat16, device_map="cuda") image = pipe( prompt="a white paper cup", image=image, mask_image=mask, height=1632, width=1232, guidance_scale=30, num_inference_steps=50, max_sequence_length=512, generator=torch.Generator("cpu").manual_seed(0) ).images[0] image.save(f"flux-fill-dev.png") - Notebooks
- Google Colab
- Kaggle
Flux.1Fill-dev-nf4
This is a custom Flux.1 Fill pipeline that combines:
- Base pipeline:
black-forest-labs/FLUX.1-dev - Transformer:
sayakpaul/FLUX.1-Fill-dev-nf4 - Text Encoder 2:
sayakpaul/FLUX.1-Fill-dev-nf4
Usage
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"CutePickle/FLUX.1-Fill-dev-nf4",
torch_dtype=torch.bfloat16
)
pipe.enable_model_cpu_offload()
image = pipe(
prompt="A cyberpunk cityscape at night",
image=init_image,
mask_image=mask
).images[0]
image.save("output.png")
- Downloads last month
- 15
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support
Model tree for CutePickle/FLUX.1-Fill-dev-nf4
Base model
black-forest-labs/FLUX.1-dev