Instructions to use herb786/Flux2-chiquito-base-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use herb786/Flux2-chiquito-base-9B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("herb786/Flux2-chiquito-base-9B", 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
Configuration Parsing Warning:In config.json: "quantization_config.modules_to_not_convert" must be an array
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
- Modelo cuantizado para black-forest-labs/FLUX.2-klein-base-9B.
- Este modelo fue cuantizado con una GPU L4 con la herramienta torchao en su versi贸n 0.18.0 con la intenci贸n de reducir el consumo de memoria.
- Cargar de la manera acostumbrada con diffusers. Funciona con diffusers 0.41.0.dev0.
Puedes ver tu versi贸n de torchao y diffusers en tu jupyter notebook con este comando
%pip show torchao diffusers
This model falls under the FLUX Non-Commercial License.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support