Instructions to use nunchaku-ai/nunchaku-flux.1-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nunchaku-ai/nunchaku-flux.1-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("nunchaku-ai/nunchaku-flux.1-dev", 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
Nunchaku not loading .safetensor file
#1
by tsolful - opened
I have nunchaku working with https://civitai.com/models/686814/jib-mix-flux?modelVersionId=1595633 which is a folder, but i downloaded nunchaku flux dev safetensor and its not loading into the dit loader
Are you getting the error (or what error message are you getting @tsolful ) that it's missing a config.json file? I know that the example .py for usage says to use the full path to the .safetensor file, but wouldn't it make sense to include the .config file?
Ah, for myself, the fix, if you want to use a specific safetensor file rather than specifying a folder with a config.json file is to upgrade to the latest nunchaku, which official release is 0.3.2. I was on 0.2.0!