Instructions to use katuni4ka/tiny-random-flux-fill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use katuni4ka/tiny-random-flux-fill with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("katuni4ka/tiny-random-flux-fill", 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
What is this?
#1
by Freefall - opened
IS this suppose to be a smaller version of flux fill? Did the file get removed?
Which file do you mean?
This is tiny model with random weights used only for model architecture debug and internal testing in some HuggingFace Libraries. There is no intention to use it in production and train/finetune this model to get some valid prediction.