Instructions to use Ffgsd/lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ffgsd/lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zai-org/GLM-Image", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Ffgsd/lora") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
| Code to automate execution of the tests and evaluate the results. | |
| Distributed as a `custom node`, and can be installed by copying or simlinking to the `custom_nodes` directory. | |
| Requires that ffprobe be available and added to the path. Note that imageio-ffmpeg does not bundle ffprobe. | |
| When installed, it adds a new sidebar tab to automate running one, or a folder of tests. This requires that the `Use new menu and workflow management` setting not be disabled | |