Instructions to use frdelga/flux-dev-lora-trainer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use frdelga/flux-dev-lora-trainer 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-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("frdelga/flux-dev-lora-trainer") prompt = "FRD_PC" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download trained_model.tar from frdelga/flux-dev-lora-trainer: direct link, hf CLI and curl.
- Browser
- Download file 172 MB
-
https://huggingface.co/frdelga/flux-dev-lora-trainer/resolve/main/trained_model.tar
- Command line
-
hf download hf://frdelga/flux-dev-lora-trainer/trained_model.tar
-
curl -L -o trained_model.tar https://huggingface.co/frdelga/flux-dev-lora-trainer/resolve/main/trained_model.tar
172 MB
- Xet hash:
- d4af7b12fb4741cd7cb9be42c4805f85a03cf02a7404ac6d2f29a69dca9149b3
- Size of remote file:
- 172 MB
- SHA256:
- c5b964883bef10fe174c8e3beb19c4fe2d6705153ccb90ed363f1523be18af18
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.